© 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. 18835
    Prev
    Next
    INDEX
    Explanations

    Chinese 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
    亨
    -0.28
    å°ı
    -0.28
    jec
    -0.27
    çĪ±
    -0.26
     ante
    -0.26
    dek
    -0.26
    TER
    -0.26
    å¾·
    -0.25
    esc
    -0.25
     Aires
    -0.25
    POSITIVE LOGITS
    许
    0.47
    éģĨ
    0.47
    ç¨ĭ
    0.41
    è°¢éŁµ
    0.41
    èĮĥåĨ°
    0.40
    ä½ķ
    0.40
    許
    0.39
    è°¢
    0.39
    èĮĥ
    0.38
    å½Ń
    0.36
    Activations Density 2.204%

    No Known Activations