© 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. 12-TRANSCODER-HP
    7. 23198
    Prev
    Next
    INDEX
    Explanations

    bomb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dry
    -0.28
     errorCallback
    -0.28
    .createFrom
    -0.26
    å¹²
    -0.26
    çħ§æł·
    -0.25
    åĸ
    -0.24
     kuruluÅŁ
    -0.24
     ENTITY
    -0.24
    lander
    -0.24
    StateException
    -0.23
    POSITIVE LOGITS
    vi
    0.29
    pad
    0.29
    OI
    0.28
    moment
    0.28
    ddf
    0.28
     moment
    0.28
    VI
    0.27
    umbs
    0.27
    ipo
    0.26
     Moment
    0.26
    Activations Density 0.001%

    No Known Activations