© 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. 32-TRANSCODER-HP
    7. 41492
    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_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regions
    -0.33
    åľ°æĸ¹
    -0.32
    åľ°åĮº
    -0.31
    -region
    -0.30
     districts
    -0.30
     region
    -0.29
    (loc
    -0.29
     provinces
    -0.28
    Regions
    -0.28
    åĮºåŁŁ
    -0.28
    POSITIVE LOGITS
    人身
    0.28
     günlük
    0.27
    个å°ı
    0.25
    ç®±
    0.24
    åºĬ
    0.24
    æĸĩèīº
    0.24
    plx
    0.24
    LETE
    0.24
    æĸĩä½ĵ
    0.23
    ç«ĭåį³
    0.23
    Activations Density 0.003%

    No Known Activations