© 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. 149271
    Prev
    Next
    INDEX
    Explanations

    blockage

    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
     ÅĽwi
    -0.29
    uci
    -0.29
    icy
    -0.28
    iras
    -0.27
    liner
    -0.27
    ListComponent
    -0.26
     бан
    -0.26
    ivery
    -0.26
     zak
    -0.25
    æĥ¶
    -0.25
    POSITIVE LOGITS
     drains
    0.28
     opposing
    0.25
    没äºĨ
    0.25
    åĪ°ä½į
    0.25
    anness
    0.24
     opposed
    0.24
    溶解
    0.24
     Integrity
    0.24
    |int
    0.24
    accessToken
    0.24
    Activations Density 0.113%

    No Known Activations