© 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. 23437
    Prev
    Next
    INDEX
    Explanations

    Challenger

    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
    åĻ¨åħ·
    -0.38
    设å¤ĩ
    -0.35
    è£ħç½®
    -0.35
     devices
    -0.35
    è¨ŃåĤĻ
    -0.33
    åĻ¨
    -0.32
    åĻ¨æĿIJ
    -0.32
    åĻ¨æ¢°
    -0.32
    hardware
    -0.31
    [obj
    -0.31
    POSITIVE LOGITS
    çĶŁç´ł
    0.26
    ķ
    0.25
    gment
    0.25
    çĶŁ
    0.25
    ExecutionContext
    0.25
    endoza
    0.25
     seam
    0.25
    ions
    0.25
    ynomial
    0.24
     REST
    0.24
    Activations Density 0.001%

    No Known Activations