© 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. 22-TRANSCODER-HP
    7. 112459
    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_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ·±æ¸Ĭ
    -0.27
     woes
    -0.26
     credentials
    -0.25
     cy
    -0.23
     оÑĩ
    -0.23
    à¸Ľà¸£à¸°à¸Ĭา
    -0.23
    hood
    -0.23
     worse
    -0.23
     Beast
    -0.23
     Sting
    -0.23
    POSITIVE LOGITS
    rouw
    0.34
    bserv
    0.30
    åıĸ
    0.30
    æīįæľī
    0.29
    leys
    0.28
    swers
    0.27
    raft
    0.27
    bras
    0.26
    æīį
    0.26
    广æĴŃ
    0.25
    Activations Density 0.026%

    No Known Activations