© 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. 162433
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    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
    .toggle
    -0.27
    ie
    -0.25
    nil
    -0.25
     Hy
    -0.24
    toggle
    -0.24
    æĥ³
    -0.24
    xbd
    -0.24
    注æĦı
    -0.23
    èĽĭ
    -0.23
    urn
    -0.23
    POSITIVE LOGITS
    太快
    0.29
    arged
    0.27
    ertime
    0.25
    æĬ¼ãģĹ
    0.25
    éĻŁ
    0.25
     breathing
    0.25
    çĮ®
    0.24
    -common
    0.24
    leccion
    0.23
    SelectedItem
    0.23
    Activations Density 0.003%

    No Known Activations