© 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. 149413
    Prev
    Next
    INDEX
    Explanations

    Computer code and file paths

    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
    åĪ¸
    -0.26
    æݪ
    -0.25
    ugo
    -0.25
     пÑĢедмеÑĤ
    -0.25
     demanding
    -0.24
    èŨ
    -0.23
    è·¨
    -0.23
     Package
    -0.23
     literature
    -0.23
     Literature
    -0.23
    POSITIVE LOGITS
     Austral
    0.30
    åľ°çIJĥ
    0.28
    太éĺ³åŁİ
    0.28
     planet
    0.26
    澳大åĪ©äºļ
    0.25
    afari
    0.25
    åħĥ件
    0.25
    ç»ĪçĶŁ
    0.25
     turbulence
    0.24
    CALE
    0.24
    Activations Density 0.027%

    No Known Activations