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. 130058
    Prev
    Next
    INDEX
    Explanations

    Organizations and business

    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
    har
    -0.25
    èĤ¡
    -0.24
    ---------↵
    -0.24
     loc
    -0.24
    车ä¸Ĭ
    -0.24
    struct
    -0.24
     simp
    -0.23
     lig
    -0.23
    Preview
    -0.23
    .Scanner
    -0.23
    POSITIVE LOGITS
     drill
    0.27
    clist
    0.26
    cff
    0.25
     пÑĥ
    0.24
    eos
    0.24
    jee
    0.24
    statusCode
    0.24
    çļĦ人çĶŁ
    0.24
    abei
    0.23
    akens
    0.23
    Activations Density 0.000%

    No Known Activations