© 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. 162510
    Prev
    Next
    INDEX
    Explanations

    smart

    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
    eed
    -0.25
     Competitive
    -0.25
     session
    -0.24
    dro
    -0.24
    /pub
    -0.23
    Average
    -0.23
     responders
    -0.22
     encoded
    -0.22
    esper
    -0.22
    Increment
    -0.22
    POSITIVE LOGITS
    楼ä¸Ĭ
    0.28
    ::-
    0.27
    è´¯
    0.27
    ObjectContext
    0.26
    åĽŃ
    0.26
    æł¡å¤ĸ
    0.25
    ä¸Ģå¼Ģå§ĭ
    0.25
     vice
    0.25
    çŁ³åĮĸ
    0.25
    åºľ
    0.24
    Activations Density 0.012%

    No Known Activations