© 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. 151304
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    çĽĴåŃIJ
    -0.30
     Planet
    -0.27
    fällig
    -0.27
    ACL
    -0.27
    ufs
    -0.25
    ellite
    -0.25
    kg
    -0.25
    Fresh
    -0.25
    ah
    -0.25
    Planet
    -0.25
    POSITIVE LOGITS
    认è¯Ĩ
    0.25
     Contribution
    0.24
    beer
    0.24
    YS
    0.24
     Lonely
    0.24
    IRON
    0.24
    ORK
    0.24
    渥
    0.24
    奸
    0.24
    wd
    0.24
    Activations Density 0.006%

    No Known Activations