© 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. 163321
    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
    ÑĥÑģÑĤ
    -0.30
     relics
    -0.27
    osite
    -0.26
    ä¹Łæĺ¯éĿŀ常
    -0.25
     tuner
    -0.24
    æݨä»ĭä¼ļ
    -0.24
    èĩĨ
    -0.24
    ä¼ī
    -0.24
    å¾Īæĺ¯
    -0.24
    è¦ģ说
    -0.23
    POSITIVE LOGITS
    irm
    0.26
     Copy
    0.26
    .Copy
    0.25
    agi
    0.25
     DM
    0.24
    ql
    0.24
    æıī
    0.24
    鸣
    0.23
     TP
    0.23
    amil
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.