© 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. 31-TRANSCODER-HP
    7. 18866
    Prev
    Next
    INDEX
    Explanations

    IT/Project Context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     management
    -0.28
     black
    -0.28
    书
    -0.27
    çĻ»è®°
    -0.26
    (typ
    -0.25
    è°±
    -0.25
    ä¸įçĶ±
    -0.25
     map
    -0.24
    jad
    -0.24
     spray
    -0.24
    POSITIVE LOGITS
    (Project
    0.30
    LOB
    0.29
     tÃŃch
    0.28
    çĥĻ
    0.28
    ephy
    0.27
     Operation
    0.27
    (Operation
    0.27
    æĸ¯åŁº
    0.26
    appear
    0.26
    æĸ½å·¥çİ°åľº
    0.26
    Activations Density 0.209%

    No Known Activations