© 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. 162444
    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
    款
    -0.26
    мÑĭÑĪ
    -0.25
     designing
    -0.24
    沿
    -0.24
     ejac
    -0.24
    è¿Ļ家åħ¬åı¸
    -0.23
     ÙĨÙģسÙĩ
    -0.23
     azi
    -0.23
    pta
    -0.23
    lla
    -0.23
    POSITIVE LOGITS
    紧紧
    0.29
    å¼Ģ
    0.27
    ä¸Ĭåįĩ
    0.26
    壮
    0.26
    å¦Ĥä½ķåİ»
    0.26
    è¶ħ级
    0.25
    èľĪ
    0.25
    壯
    0.24
    é¾ĻéŨ
    0.24
    åİŁæĿ¥
    0.24
    Activations Density 0.065%

    No Known Activations

    This feature has no known activations.