© 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. 24-TRANSCODER-HP
    7. 149162
    Prev
    Next
    INDEX
    Explanations

    meal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    etat
    -0.29
    eer
    -0.28
    etri
    -0.26
    èļķ
    -0.25
    强çĥĪ
    -0.25
    ç»ĵæĻ¶
    -0.25
    пÑĢÑı
    -0.24
    otate
    -0.24
    赫
    -0.24
    rade
    -0.24
    POSITIVE LOGITS
    ä¸ĢæĹ¥
    0.31
    orie
    0.30
    ific
    0.28
     replica
    0.24
    -INF
    0.24
    ths
    0.24
    loid
    0.24
     complement
    0.24
    icular
    0.23
    icles
    0.23
    Activations Density 1.441%

    No Known Activations