© 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. 163475
    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
     Ze
    -0.28
    uting
    -0.27
    çĻ¾
    -0.26
     Syn
    -0.26
    ex
    -0.26
    çļĦæĢģ度
    -0.25
    产
    -0.25
    çļĦéĹ®é¢ĺ
    -0.25
    åĪ°æľĢåIJİ
    -0.24
    -kind
    -0.24
    POSITIVE LOGITS
    @student
    0.29
     corpor
    0.28
    affles
    0.28
    å»ĵ
    0.25
    kor
    0.25
     corridor
    0.24
    岸
    0.24
    çİĭåĽ½
    0.24
     locality
    0.23
    çĸ¾çĹħçļĦ
    0.23
    Activations Density 0.003%

    No Known Activations