© 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. 163516
    Prev
    Next
    INDEX
    Explanations

    Something being wrong/incorrect

    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
    PACE
    -0.27
    곤
    -0.26
    ensus
    -0.26
    paces
    -0.25
    .isNullOrEmpty
    -0.24
    uffix
    -0.24
    pace
    -0.24
     Mechanics
    -0.24
     PackageManager
    -0.24
    ËĿ
    -0.24
    POSITIVE LOGITS
     prod
    0.30
    prod
    0.28
     fred
    0.27
    nore
    0.27
     behavior
    0.26
    家ä¼Ļ
    0.26
    éĢīæīĭ
    0.26
    cases
    0.26
     cases
    0.26
    au
    0.25
    Activations Density 0.019%

    No Known Activations