© 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. 150435
    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
    举æĬ¥çĶµè¯Ŀ
    -0.27
    解æĶ¾åĨĽ
    -0.27
    ï¬Ĥ
    -0.26
    æĭħ
    -0.25
     Evelyn
    -0.25
    AreaView
    -0.24
     Creek
    -0.24
    edReader
    -0.24
    clearfix
    -0.24
    欢è¿İ
    -0.24
    POSITIVE LOGITS
    راء
    0.28
    -util
    0.27
     pneum
    0.27
     sigma
    0.26
    ayas
    0.25
    å«
    0.24
    寸
    0.23
    vestment
    0.23
    alta
    0.23
    è¿ĩå¤ļ
    0.23
    Activations Density 3.168%

    No Known Activations

    This feature has no known activations.