© 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. 163790
    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
    -backend
    -0.27
    æĶ¶æĶ¯
    -0.25
    infos
    -0.25
    å¢ŀæĶ¶
    -0.25
    ingers
    -0.25
     intermediary
    -0.25
    é²µ
    -0.25
    ä¸ĵåįĸåºĹ
    -0.24
    yla
    -0.24
    .za
    -0.24
    POSITIVE LOGITS
    hei
    0.29
    FFE
    0.27
    hé
    0.26
    .jackson
    0.26
     ÑĢам
    0.25
    еÑģÑĤво
    0.24
    åĬ©ãģij
    0.24
    KEN
    0.24
    heartbeat
    0.24
    ffects
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.