© 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. 162305
    Prev
    Next
    INDEX
    Explanations

    non

    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
    åīįèĢħ
    -0.29
    åįķåħĥ
    -0.27
    ecc
    -0.26
    ulares
    -0.26
    å§Ķ
    -0.25
    åĢŁçĶ¨
    -0.25
     EXPRESS
    -0.25
    åħ¶æ¬¡æĺ¯
    -0.25
    æīĵåİĭ
    -0.24
    xCC
    -0.24
    POSITIVE LOGITS
     generally
    0.30
    enville
    0.29
     rejo
    0.28
     context
    0.28
     right
    0.27
     indiv
    0.26
     plausible
    0.26
    ä¸įå½±åĵį
    0.26
    æĿĥåĪ©
    0.25
    jo
    0.25
    Activations Density 0.001%

    No Known Activations