© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112808
    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
     flag
    -0.32
     Flag
    -0.27
    flag
    -0.27
    FLAG
    -0.27
    森
    -0.27
    stan
    -0.26
    trag
    -0.26
    t
    -0.25
    noc
    -0.25
    adian
    -0.25
    POSITIVE LOGITS
    ertest
    0.29
     builds
    0.28
    éĬ®
    0.27
    (builder
    0.27
    æī©å»º
    0.27
    äºĨä¸Ģåı¥
    0.25
    âĨĻ
    0.25
    (groups
    0.25
    .Abstractions
    0.24
    build
    0.24
    Activations Density 0.013%

    No Known Activations