© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149699
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä½Ļ
    -0.28
    è¿ĶåĽŀæIJľçĭIJ
    -0.26
    anges
    -0.25
     excess
    -0.24
    Registr
    -0.24
    æĹłæĥħ
    -0.24
    çĥ©
    -0.24
    istle
    -0.24
    ByPrimaryKey
    -0.24
    .union
    -0.24
    POSITIVE LOGITS
    logue
    0.26
    Miller
    0.23
     onCancel
    0.23
    åģļ大
    0.23
    ç«ĭ马
    0.23
    æ¶Īæŀģ
    0.23
     Aut
    0.23
     benef
    0.23
    placeholders
    0.23
     Amid
    0.23
    Activations Density 2.462%

    No Known Activations

    This feature has no known activations.