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. 15349
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     extent
    -0.29
    iston
    -0.27
     import
    -0.27
    heits
    -0.26
    .ts
    -0.25
    peÅĤ
    -0.25
     https
    -0.24
    æ¸ħè¿ľ
    -0.24
     Down
    -0.24
     tune
    -0.24
    POSITIVE LOGITS
     tablename
    0.29
    ijľ
    0.26
    IRON
    0.25
     ylabel
    0.25
     WARRANT
    0.25
     getDefault
    0.24
    osaurs
    0.24
    çĺ¥
    0.24
    igraphy
    0.24
    ocytes
    0.24
    Activations Density 0.003%

    No Known Activations