© 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. 163332
    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
    éŀŃ
    -0.30
    eon
    -0.29
     Reyn
    -0.26
    ctors
    -0.26
    anja
    -0.26
    ass
    -0.25
    onaut
    -0.25
     اÙĦØŃر
    -0.25
     Byte
    -0.25
     Casc
    -0.25
    POSITIVE LOGITS
    ä½Ĩå®ĥ
    0.25
    (DIR
    0.25
     david
    0.25
    FFE
    0.25
    agy
    0.24
    ä½Ĩ对äºİ
    0.24
     payday
    0.24
    ground
    0.24
    çijľ
    0.23
    ä¸ĢéĿ¢
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.