© 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. 163779
    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
    rie
    -0.33
    ToOne
    -0.28
    åįĥä¼ı
    -0.27
    ograd
    -0.26
     ta
    -0.26
    linky
    -0.26
    失
    -0.25
    links
    -0.25
    åij¼
    -0.25
    SM
    -0.24
    POSITIVE LOGITS
     каÑĩ
    0.27
    BEST
    0.24
     spécialisé
    0.24
    天涯
    0.24
    ahkan
    0.23
    åݿ级
    0.23
     Terrace
    0.23
    ecer
    0.23
    enz
    0.23
    _FINE
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.