© 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. 150869
    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
    ombat
    -0.30
    ritz
    -0.27
     break
    -0.27
    转æĬĺ
    -0.27
    sein
    -0.26
    members
    -0.26
    ä¸ĩ个
    -0.25
     kÃŃnh
    -0.25
    break
    -0.25
    enames
    -0.24
    POSITIVE LOGITS
    ett
    0.27
    esting
    0.27
    ="__
    0.25
    .inspect
    0.25
     Inspection
    0.25
     dilig
    0.25
    çĬĦ
    0.24
    jal
    0.24
     Rossi
    0.23
    æĥħåĨµè¿Ľè¡Į
    0.23
    Activations Density 0.215%

    No Known Activations

    This feature has no known activations.