© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54070
    Prev
    Next
    INDEX
    Explanations

    computer or programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Previous
    -0.32
    以åīį
    -0.29
    (previous
    -0.28
     predecessors
    -0.28
    ione
    -0.27
    ä¹ĭåīįçļĦ
    -0.27
    åīįæĸ¹
    -0.26
    (before
    -0.26
     previous
    -0.26
    _previous
    -0.26
    POSITIVE LOGITS
     right
    0.43
    right
    0.35
     indefinitely
    0.34
     be
    0.32
     RIGHT
    0.31
    åı³ä¾§
    0.30
     accordingly
    0.30
     differently
    0.28
     kilometers
    0.28
    ÐŁÑĢав
    0.28
    Activations Density 0.032%

    No Known Activations