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. 1701
    Prev
    Next
    INDEX
    Explanations

    gir

    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
    çϾèĬ±
    -0.26
     beams
    -0.26
    guns
    -0.25
    .tight
    -0.25
    dit
    -0.25
    ä¸įçķĻ
    -0.25
    pany
    -0.25
    ivant
    -0.24
    -pe
    -0.24
    åĽ¢ä½ĵ
    -0.24
    POSITIVE LOGITS
    oproject
    0.25
    @m
    0.25
    ellig
    0.25
    proj
    0.24
    å¾Ĺèµ·
    0.24
     overrides
    0.24
     Amendment
    0.23
     Commissioners
    0.23
     indexer
    0.23
    olf
    0.23
    Activations Density 0.788%

    No Known Activations