© 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. 9-TRANSCODER-HP
    7. 29751
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ身
    -0.28
    mailto
    -0.26
    è¿Ľé¡¹
    -0.25
    eral
    -0.24
    满满çļĦ
    -0.24
    ERAL
    -0.23
    æµij身
    -0.23
     Transitional
    -0.23
     Article
    -0.23
     Plate
    -0.23
    POSITIVE LOGITS
    ä¼Ļ
    0.30
     VIR
    0.27
    entropy
    0.26
     sweeps
    0.25
     leak
    0.25
    _ENT
    0.25
     personals
    0.25
    å©¿
    0.25
     nuôi
    0.24
    ocks
    0.24
    Activations Density 0.838%

    No Known Activations