© 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. 162511
    Prev
    Next
    INDEX
    Explanations

    Informal writing/blog posts

    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
     Persistent
    -0.28
    resolve
    -0.27
    plier
    -0.26
    Ø·ÙĨ
    -0.26
    æĦı
    -0.25
    Resolve
    -0.25
    Pers
    -0.25
    OPY
    -0.25
    ov
    -0.24
     Pers
    -0.24
    POSITIVE LOGITS
    isy
    0.27
    è¿ĩå¾Ĺ
    0.26
    大å°ı
    0.26
    ize
    0.25
    ized
    0.25
    ãĤĮãģ¾ãģĻ
    0.25
     Embassy
    0.24
    ISE
    0.24
     drop
    0.24
    好çľĭ
    0.24
    Activations Density 0.022%

    No Known Activations