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. 1699
    Prev
    Next
    INDEX
    Explanations

    support

    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
    unts
    -0.29
    ovies
    -0.26
    odega
    -0.25
    ató
    -0.24
    俯
    -0.24
    allenges
    -0.24
     Manson
    -0.24
    ÑĢÑĥз
    -0.24
    ivist
    -0.23
    <Token
    -0.23
    POSITIVE LOGITS
     Nation
    0.29
    ola
    0.29
    akit
    0.27
    NC
    0.26
     pu
    0.26
    umin
    0.25
    aura
    0.25
     Polar
    0.24
     label
    0.24
     prefixed
    0.24
    Activations Density 0.001%

    No Known Activations