© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96968
    Prev
    Next
    INDEX
    Explanations

    u

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     incumbent
    -0.29
    æĬ½
    -0.27
    pins
    -0.27
    ni
    -0.26
     drawing
    -0.26
    åĩĿ
    -0.26
     Pin
    -0.25
    skin
    -0.25
     Drawing
    -0.25
    pin
    -0.25
    POSITIVE LOGITS
    olith
    0.31
    纵
    0.28
    ÑĢе
    0.28
    箧
    0.27
     phé
    0.27
    łéĻ¤
    0.27
    ortal
    0.26
    AndGet
    0.25
    /Public
    0.24
     Administration
    0.24
    Activations Density 0.792%

    No Known Activations