© 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. 162303
    Prev
    Next
    INDEX
    Explanations

    obstacles or obstructions

    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
    æĸĹ
    -0.32
    ÑģеÑĤ
    -0.29
    å¸Ń
    -0.27
     Decl
    -0.27
    æĸĩåĮĸçļĦ
    -0.26
    erras
    -0.26
    åı¤æĢª
    -0.26
    éªĮ
    -0.25
    rene
    -0.24
    ieurs
    -0.24
    POSITIVE LOGITS
    svp
    0.28
    IPH
    0.27
    azel
    0.26
    èĿİ
    0.25
    à¸ij
    0.24
     pathway
    0.23
    olta
    0.23
    .general
    0.23
     Ballard
    0.23
     taxonomy
    0.23
    Activations Density 0.013%

    No Known Activations