© 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. 162535
    Prev
    Next
    INDEX
    Explanations

    Separator symbols

    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
    irectional
    -0.27
    gos
    -0.25
    áo
    -0.25
    adamente
    -0.25
    lei
    -0.24
    Ĩµ
    -0.23
    okus
    -0.23
    idar
    -0.22
    ário
    -0.22
    IRE
    -0.22
    POSITIVE LOGITS
     and
    0.72
    åĴĮ
    0.67
    以åıĬ
    0.65
    åıĬ
    0.64
    åĴĮ个人
    0.61
     vÃł
    0.58
     or
    0.57
    åĴĮ社ä¼ļ
    0.55
    åĴĮæĬĢæľ¯
    0.54
    åĴĮåħ¶ä»ĸ
    0.54
    Activations Density 0.001%

    No Known Activations