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. 54160
    Prev
    Next
    INDEX
    Explanations

    legal/political documents

    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
    æ¡£
    -0.36
    ifier
    -0.28
    æīĭä¸Ĭ
    -0.27
    æĬ«
    -0.26
     mas
    -0.26
     staff
    -0.25
     Staff
    -0.25
     cave
    -0.25
    ä¹ŀ
    -0.24
    elda
    -0.24
    POSITIVE LOGITS
     defe
    0.28
    hosts
    0.26
    çĸĻ
    0.25
     Het
    0.25
    fv
    0.25
     Ax
    0.24
     uniformly
    0.24
    ALLY
    0.23
    avax
    0.23
     specialty
    0.23
    Activations Density 0.006%

    No Known Activations