© 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. 95209
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     tell
    -0.41
    åijĬè¯ī
    -0.41
     telling
    -0.40
    Tell
    -0.38
     Tell
    -0.38
     tells
    -0.38
    tell
    -0.37
    åijĬ訴
    -0.36
     told
    -0.35
    .tell
    -0.33
    POSITIVE LOGITS
     generalized
    0.32
    emed
    0.31
     dismissed
    0.30
    è¿Ļæĺ¯æĪij
    0.27
    表示
    0.25
    .kotlin
    0.25
    arg
    0.25
    UEL
    0.25
     dismiss
    0.24
    å¾Īæĺİæĺ¾
    0.24
    Activations Density 0.005%

    No Known Activations