© 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. 162208
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act · gemini-2.0-flash
    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
    缺失
    -0.30
    紧迫
    -0.26
    éĥ½éľĢè¦ģ
    -0.25
     subs
    -0.24
    说ä¸įåĩº
    -0.24
    è¿Ļä¹Ī说
    -0.24
    aut
    -0.24
    说å®ŀè¯Ŀ
    -0.24
     worldwide
    -0.24
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.28
     mb
    0.28
     Till
    0.27
    ır
    0.27
     bars
    0.26
    ðŁı»
    0.26
     Wr
    0.25
    kir
    0.25
     ..↵↵
    0.25
    ackbar
    0.24
    Activations Density 0.097%

    No Known Activations