© 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. 32-TRANSCODER-HP
    7. 41488
    Prev
    Next
    INDEX
    Explanations

    toxins and pathology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    snow
    -0.27
     wax
    -0.27
    óc
    -0.26
     Wax
    -0.26
    ONY
    -0.26
    missing
    -0.26
    çļ
    -0.25
    anon
    -0.25
     snow
    -0.25
    scaling
    -0.25
    POSITIVE LOGITS
    lette
    0.25
    inet
    0.24
    alli
    0.24
    使
    0.24
     tie
    0.24
    orghini
    0.23
    ç¼Ģ
    0.23
    èijĽ
    0.23
    貫
    0.23
    aceous
    0.23
    Activations Density 0.003%

    No Known Activations