© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18442
    Prev
    Next
    INDEX
    Explanations

    variations of "poss"

    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
    åĪĨæķ°çº¿
    -0.30
    åĪĨåĮĸ
    -0.25
    æݨåĩº
    -0.25
    /interfaces
    -0.24
    幡
    -0.24
     Pills
    -0.24
    èĪIJ
    -0.24
    alar
    -0.23
    orton
    -0.23
    åĺĺ
    -0.23
    POSITIVE LOGITS
     possess
    1.47
     poss
    1.46
     Poss
    1.43
    æĭ¥æľī
    1.40
     possession
    1.37
    poss
    1.36
    æĭ¥
    1.32
     possesses
    1.31
     possessed
    1.27
     possessing
    1.26
    Activations Density 23.561%

    No Known Activations