© 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. 162438
    Prev
    Next
    INDEX
    Explanations

    Aud

    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
    ization
    -0.28
    ation
    -0.28
    iner
    -0.27
    ATED
    -0.27
    ism
    -0.27
    IZATION
    -0.27
    eer
    -0.26
    ctica
    -0.26
    .initState
    -0.25
    æ´Ļ
    -0.25
    POSITIVE LOGITS
    sweet
    0.29
    sie
    0.28
    s
    0.27
    sist
    0.26
    rup
    0.26
    sic
    0.26
    sol
    0.26
    skip
    0.25
    summer
    0.24
    笼
    0.24
    Activations Density 0.374%

    No Known Activations