© 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. 96764
    Prev
    Next
    INDEX
    Explanations

    atomic/atom

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Defender
    -0.28
    踵
    -0.26
     swallow
    -0.26
    ements
    -0.25
    DisplayName
    -0.25
    ENN
    -0.25
    èĩĨ
    -0.25
    çľ¨çľ¼
    -0.25
    çĿ
    -0.25
    roids
    -0.24
    POSITIVE LOGITS
     resolution
    0.28
     association
    0.28
     Hubb
    0.27
     hơi
    0.27
    åıij
    0.27
    clock
    0.27
    bsolute
    0.25
    åĽ¾çĶ»
    0.25
    resolution
    0.25
     limits
    0.24
    Activations Density 0.785%

    No Known Activations