© 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. 24-TRANSCODER-HP
    7. 150630
    Prev
    Next
    INDEX
    Explanations

    offense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ters
    -0.28
    ovie
    -0.26
     Plenty
    -0.26
     plentiful
    -0.26
    ieurs
    -0.25
    elves
    -0.25
     Phantom
    -0.25
    avors
    -0.25
     FOLLOW
    -0.25
     LEN
    -0.24
    POSITIVE LOGITS
    _APPS
    0.30
     family
    0.28
     by
    0.28
     yet
    0.27
    7
    0.27
     not
    0.26
     Media
    0.25
    å°ļ书
    0.25
    ble
    0.25
     based
    0.25
    Activations Density 0.135%

    No Known Activations