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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162267
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç³Ĭæ¶Ĥ
    -0.31
     coincidence
    -0.26
     similarity
    -0.25
     coinc
    -0.25
     UPC
    -0.24
     mutual
    -0.24
     decrypt
    -0.24
    loyd
    -0.24
     joint
    -0.23
     Mutual
    -0.23
    POSITIVE LOGITS
    thon
    0.31
    ви
    0.28
    gan
    0.27
    mith
    0.26
    rary
    0.25
    åĩ»è´¥
    0.24
    qli
    0.24
    ÙĤاتÙĦ
    0.24
    Ļ¨
    0.24
     Vict
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.