© 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. 151271
    Prev
    Next
    INDEX
    Explanations

    web page / technical documentation

    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
    amental
    -0.28
    -ob
    -0.28
    ellation
    -0.27
    .ly
    -0.26
     ded
    -0.26
    åĬ£
    -0.25
    vec
    -0.25
    itional
    -0.25
    amentals
    -0.24
    entlich
    -0.24
    POSITIVE LOGITS
    oze
    0.31
    owi
    0.29
    æĸ°è§Ħ
    0.27
     bowls
    0.25
     Bowl
    0.24
    åľ¨çĶŁæ´»ä¸Ń
    0.24
    IDL
    0.24
     bowl
    0.23
    setItem
    0.23
    /'.
    0.23
    Activations Density 0.283%

    No Known Activations