© 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. 53477
    Prev
    Next
    INDEX
    Explanations

    Dr

    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
    éľĩ
    -0.27
    Arch
    -0.27
    pose
    -0.27
    esen
    -0.27
    åĩ«
    -0.26
     æŀ
    -0.26
    äng
    -0.26
    osen
    -0.26
    _mark
    -0.25
    éķ·
    -0.25
    POSITIVE LOGITS
    vio
    0.28
    åĬĽè¿ĺæĺ¯
    0.28
    è¿Ļæł·è¯´
    0.28
    .serializer
    0.25
    æ¾İ
    0.25
    ç»ĨåĪĻ
    0.25
     mistress
    0.25
    èIJİ缩
    0.24
     PGA
    0.24
    pig
    0.23
    Activations Density 0.005%

    No Known Activations