© 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. 149221
    Prev
    Next
    INDEX
    Explanations

    of

    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
    bol
    -0.27
    票价
    -0.26
    ocks
    -0.26
     Others
    -0.26
     Inf
    -0.25
     hamm
    -0.25
    缮åīįæŃ£åľ¨
    -0.25
    .inf
    -0.25
    ĤŃ
    -0.24
    强迫
    -0.24
    POSITIVE LOGITS
    tec
    0.29
    coni
    0.29
    ooth
    0.28
    å½ĵæŶ
    0.28
    utm
    0.26
    rogram
    0.26
    intel
    0.25
    ória
    0.25
    ORIA
    0.25
    å½ĵæŶçļĦ
    0.25
    Activations Density 1.033%

    No Known Activations