© 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. 31-TRANSCODER-HP
    7. 19629
    Prev
    Next
    INDEX
    Explanations

    Locations and place descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apon
    -0.26
    VML
    -0.25
    éĺı
    -0.24
    eps
    -0.24
     shallow
    -0.24
    ÑģÑĤÑĢой
    -0.24
     Harlem
    -0.24
    Storage
    -0.23
    ä¹ĭäºī
    -0.23
    heim
    -0.23
    POSITIVE LOGITS
    çĪ±ä½ł
    0.26
     ten
    0.26
     ÐĽÐ¸
    0.25
     trụ
    0.25
    ded
    0.25
    ce
    0.25
    åıĭæĥħ
    0.25
    å´ĩæĭľ
    0.24
    æ³ķ人
    0.24
    æķ¬ä¸ļ
    0.23
    Activations Density 0.102%

    No Known Activations