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. 2-TRANSCODER-HP
    4. 210
    Prev
    Next
    INDEX
    Explanations

    reserve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EXT
    -0.26
    qui
    -0.24
    wart
    -0.24
     ÑĢаÑģпÑĢ
    -0.24
     vite
    -0.24
     Frm
    -0.23
     vehement
    -0.23
    ATED
    -0.23
     EXT
    -0.23
     Incorrect
    -0.23
    POSITIVE LOGITS
    ingu
    0.25
    inson
    0.25
    erson
    0.25
    æIJģ
    0.25
    ÑĢад
    0.24
     ourselves
    0.24
    оÑĩки
    0.24
    à¦Ľ
    0.24
    sing
    0.24
    çĽĶ
    0.24
    Activations Density 43.292%

    No Known Activations