© 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. 162522
    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
    otics
    -0.28
    ERT
    -0.27
    nsic
    -0.26
    lox
    -0.26
    [assembly
    -0.26
    责任æĦŁ
    -0.26
    éĢ¡
    -0.25
    plaint
    -0.25
     Beginners
    -0.25
    ipline
    -0.25
    POSITIVE LOGITS
    dere
    0.31
    tas
    0.28
    arda
    0.28
    å®ŀè¡Į
    0.27
     ().
    0.27
    arr
    0.26
    igar
    0.26
    long
    0.26
    ä¸Ģè·¯
    0.26
    car
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.