© 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. 163819
    Prev
    Next
    INDEX
    Explanations

    of

    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
     vow
    -0.26
     dolls
    -0.24
    asar
    -0.24
    gram
    -0.24
    age
    -0.24
     rout
    -0.24
     clearing
    -0.24
    ãģ«åIJij
    -0.23
    翻身
    -0.23
    .xaml
    -0.23
    POSITIVE LOGITS
    yte
    0.28
    æ¿Ģ
    0.27
    èIJ½
    0.26
    _exec
    0.26
     Nh
    0.25
    Knight
    0.25
    ä¼ģä¸ļ管çIJĨ
    0.25
     Xen
    0.25
     Blues
    0.24
     nei
    0.24
    Activations Density 0.007%

    No Known Activations