© 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. 33-TRANSCODER-HP
    7. 53687
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°Ł
    -0.32
     Waves
    -0.28
    纯
    -0.26
    nik
    -0.25
    缮å½ķ
    -0.25
    struk
    -0.25
    dana
    -0.25
    ç®Ĺ
    -0.25
    ç´Ķ
    -0.24
    è²»
    -0.24
    POSITIVE LOGITS
    CLU
    0.26
    鸡
    0.26
     poultry
    0.26
    iba
    0.26
    åı½
    0.25
    çIJµ
    0.25
    踢
    0.25
    åĪĨæµģ
    0.25
    ä»İåݻ年
    0.24
    婵
    0.24
    Activations Density 0.005%

    No Known Activations