© 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. 25-TRANSCODER-HP
    7. 108992
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    extended
    -0.30
     extended
    -0.26
    leanup
    -0.26
    æĸ¹éĿ¢çļĦ
    -0.26
    adjusted
    -0.25
     Unable
    -0.25
    boxing
    -0.25
    æĶ¯çº¿
    -0.25
    让èĩªå·±
    -0.25
    çħ½
    -0.24
    POSITIVE LOGITS
     FAG
    0.26
    çĦ°
    0.25
    åıijçİ°éĹ®é¢ĺ
    0.25
    getApplication
    0.24
    æľĭåıĭ
    0.23
    竣工
    0.23
    жал
    0.23
    èĢĥ
    0.23
    redd
    0.23
    agate
    0.23
    Activations Density 0.914%

    No Known Activations