Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 54508
    Prev
    Next
    INDEX
    Explanations

    Nak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Humanities
    -0.27
     bluff
    -0.27
    agements
    -0.26
    æĢ¡
    -0.25
    esy
    -0.24
    æĺł
    -0.24
    ypi
    -0.24
    ä½İä¼°
    -0.24
    缸
    -0.24
    çĶº
    -0.23
    POSITIVE LOGITS
    OKIE
    0.27
     ratified
    0.26
    istar
    0.25
    éļ¾é¢ĺ
    0.24
    LAT
    0.24
     rip
    0.24
     Kund
    0.24
    éĺij
    0.24
    è´¯éĢļ
    0.23
    ipers
    0.23
    Activations Density 0.008%

    No Known Activations