© 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. 163200
    Prev
    Next
    INDEX
    Explanations

    Code or system instructions

    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
     conjug
    -0.30
    æĵį
    -0.29
    ç¨Ģ
    -0.28
     ideal
    -0.27
     advising
    -0.27
    ä¾£
    -0.27
    çļĦä¼ĺçĤ¹
    -0.26
    aca
    -0.26
     Advis
    -0.26
    æĪIJåĬŁ
    -0.25
    POSITIVE LOGITS
     Isl
    0.27
    lineno
    0.27
    ocache
    0.26
    uvo
    0.26
    試
    0.26
    ppe
    0.26
     irreversible
    0.25
    åı·æ¥¼
    0.25
     griev
    0.25
    è¯ģæĺİ
    0.25
    Activations Density 0.000%

    No Known Activations