© 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. 88891
    Prev
    Next
    INDEX
    Explanations

    entry

    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
    Negative Logits
    icos
    -0.28
     Watches
    -0.25
     lashes
    -0.25
    vak
    -0.24
    avra
    -0.24
    autoload
    -0.24
    IMS
    -0.23
    à¤Ī
    -0.23
    erals
    -0.22
     Setting
    -0.22
    POSITIVE LOGITS
    wise
    0.33
    à¹Į
    0.27
     condition
    0.27
    prising
    0.27
    prises
    0.26
    uating
    0.26
    prise
    0.25
    ment
    0.25
    åįļçī©
    0.25
     conditions
    0.25
    Activations Density 0.180%

    No Known Activations