© 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. 150376
    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
    élection
    -0.30
    æĪ·åı£
    -0.26
    åĬ²
    -0.25
    çIJĨ
    -0.25
    çĤ¹å¤´
    -0.25
     longest
    -0.25
    lowest
    -0.24
    çŁ¥éģĵèĩªå·±
    -0.24
     возможноÑģÑĤÑĮ
    -0.23
    ohn
    -0.23
    POSITIVE LOGITS
    RAFT
    0.28
    å¿ħä¸įåı¯
    0.26
    ä¸ŃåĽ½æĸĩåĮĸ
    0.26
    -toolbar
    0.26
     Petty
    0.24
    spo
    0.24
    éĶļ
    0.24
    çĬĬ
    0.24
    .bio
    0.24
    ietf
    0.24
    Activations Density 1.955%

    No Known Activations

    This feature has no known activations.