© 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. 27-TRANSCODER-HP
    7. 56615
    Prev
    Next
    INDEX
    Explanations

    possessives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    's
    -0.45
    ’s
    -0.35
    'S
    -0.29
    ‘s
    -0.28
    çļĦåIJĪä½ľ
    -0.27
    quate
    -0.27
     Devin
    -0.26
    alse
    -0.26
    çļĦ身份
    -0.25
    çļĦåĽłç´ł
    -0.25
    POSITIVE LOGITS
    çİ©
    0.26
     бÑĥд
    0.26
    “He
    0.25
    äºĭä¸ļ
    0.24
    elden
    0.24
    åģļèµ·
    0.24
    æİ¥è¿ij
    0.23
    ml
    0.23
    warts
    0.23
    rozen
    0.23
    Activations Density 0.007%

    No Known Activations