© 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. 162680
    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
    çļĦæĪIJåĬŁ
    -0.28
     Bucks
    -0.26
    aug
    -0.25
    TTY
    -0.24
    çĭ¬
    -0.24
    滥çĶ¨
    -0.23
    defines
    -0.23
    èħ®
    -0.23
     Unlike
    -0.23
     aug
    -0.23
    POSITIVE LOGITS
     purpose
    0.30
    gettext
    0.27
     Purpose
    0.27
    åıĻè¿°
    0.27
    adro
    0.25
    phans
    0.25
    飵
    0.25
    æĻļæĬ¥
    0.24
    elier
    0.24
    æĢ»å±Ģ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.