© 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. 35-TRANSCODER-HP
    7. 40572
    Prev
    Next
    INDEX
    Explanations

    adapt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .payload
    -0.28
    (P
    -0.28
     Back
    -0.26
    =P
    -0.24
     lại
    -0.24
    /P
    -0.24
    <p
    -0.24
    mpp
    -0.23
     poil
    -0.23
    ocrates
    -0.23
    POSITIVE LOGITS
    éĢĤåºĶ
    0.60
    adapt
    0.59
    éĢĤ
    0.56
     adapted
    0.55
     adapt
    0.53
     adaptive
    0.53
    adaptive
    0.52
     adaptation
    0.51
     adap
    0.50
     Adapt
    0.48
    Activations Density 0.430%

    No Known Activations