© 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. 163119
    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
    çĦ¶
    -0.27
     odds
    -0.25
    vides
    -0.25
    åIJĦæľī
    -0.24
     sup
    -0.24
    ä»·åĢ¼éĵ¾
    -0.24
    иÑħ
    -0.24
     draft
    -0.24
    éĥ½åľ¨
    -0.24
    åºĶçĶ¨
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĪĨéĴ±
    0.27
     remembering
    0.27
    åĬłå·¥åİĤ
    0.26
    pga
    0.25
    Facing
    0.25
    è¿Ļä¹Ī大
    0.25
    è®°ä½ı
    0.25
    apsed
    0.25
    ä¸ĬéŨ
    0.25
     elimination
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.