© 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. 53568
    Prev
    Next
    INDEX
    Explanations

    naming and saying things

    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
    own
    -0.30
    Be
    -0.29
     Bee
    -0.28
     Be
    -0.28
     own
    -0.28
    mutable
    -0.27
    defs
    -0.26
     Checked
    -0.26
    	be
    -0.26
    thrown
    -0.26
    POSITIVE LOGITS
     named
    0.31
     said
    0.30
     called
    0.30
    ç¿Ĵ
    0.28
     Called
    0.27
    åı«
    0.27
    qml
    0.26
     pr
    0.26
     nicknamed
    0.26
     stated
    0.25
    Activations Density 0.071%

    No Known Activations