© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109213
    Prev
    Next
    INDEX
    Explanations

    bacterial/scientific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tens
    -0.28
    tt
    -0.27
     Virtual
    -0.26
    翳
    -0.25
    æĥķ
    -0.25
    æĢµ
    -0.25
    轻轻
    -0.25
    _VM
    -0.24
    )))↵↵↵
    -0.24
    Virtual
    -0.24
    POSITIVE LOGITS
    æݪ
    0.30
    æ¯Ķäºļ
    0.25
     Xin
    0.25
    idea
    0.24
    Mp
    0.24
    -ul
    0.24
     polled
    0.24
     parten
    0.23
    åijĬè¯ī她
    0.23
     Cruiser
    0.23
    Activations Density 0.147%

    No Known Activations