© 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. 19-TRANSCODER-HP
    7. 8806
    Prev
    Next
    INDEX
    Explanations

    Negative/difficult situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    components
    -0.29
    urations
    -0.26
    ections
    -0.26
    iators
    -0.26
    è¿Ļæĸ¹éĿ¢
    -0.25
    \Component
    -0.24
     Bend
    -0.24
    itat
    -0.24
    msgid
    -0.24
    icken
    -0.24
    POSITIVE LOGITS
     sacr
    0.26
    -focused
    0.25
    -worthy
    0.25
    åİį
    0.24
     intended
    0.24
    å¿ĥ缮
    0.24
    -del
    0.24
     automatic
    0.23
    =?,
    0.23
    ansson
    0.23
    Activations Density 0.115%

    No Known Activations