© 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. 149141
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    unts
    -0.26
    iors
    -0.26
    ä¸Ĭåįĩ
    -0.25
    éļĻ
    -0.25
    sticks
    -0.25
    æ·¬
    -0.25
    afil
    -0.25
    unt
    -0.25
    stick
    -0.23
    麥
    -0.23
    POSITIVE LOGITS
     imm
    0.28
    ctype
    0.26
    å¯Įæľī
    0.25
    athed
    0.25
    cele
    0.24
    PPP
    0.24
    unge
    0.24
    Contr
    0.23
    ambre
    0.23
     Simply
    0.23
    Activations Density 0.054%

    No Known Activations