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. 7-TRANSCODER-HP
    4. 130057
    Prev
    Next
    INDEX
    Explanations

    ls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satur
    -0.31
    寡
    -0.27
     Orig
    -0.26
    çݯçIJĥ
    -0.26
    Li
    -0.25
    FUL
    -0.24
    aly
    -0.24
    ruc
    -0.24
     obed
    -0.24
    ifer
    -0.23
    POSITIVE LOGITS
    é¡¶
    0.25
    edom
    0.25
    rale
    0.24
    踵
    0.24
    æĢĢçĿĢ
    0.24
    elige
    0.24
     apparent
    0.24
    ее
    0.24
     referral
    0.23
    .Socket
    0.23
    Activations Density 0.001%

    No Known Activations