© 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. 30-TRANSCODER-HP
    7. 95599
    Prev
    Next
    INDEX
    Explanations

    Informational or instructional content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶ä»ĸ
    -0.42
    åħ¶å®ĥ
    -0.39
    other
    -0.37
     other
    -0.36
    Other
    -0.33
     Other
    -0.33
     otras
    -0.33
    åħ¶å®ĥéĹ®é¢ĺ
    -0.31
    ä¸ĢäºĽ
    -0.31
     OTHER
    -0.31
    POSITIVE LOGITS
     pieces
    0.30
     games
    0.28
     writing
    0.27
     products
    0.27
     vendors
    0.27
     puzzle
    0.26
     articles
    0.26
     lover
    0.26
     routines
    0.26
     literature
    0.26
    Activations Density 0.903%

    No Known Activations