© 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. 88961
    Prev
    Next
    INDEX
    Explanations

    Benefit

    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
    eos
    -0.30
    æīģ
    -0.25
     inspected
    -0.24
    eil
    -0.24
     Styled
    -0.24
    æĵįåľº
    -0.23
    oze
    -0.23
    满æĦıçļĦ
    -0.23
    edo
    -0.23
    platz
    -0.23
    POSITIVE LOGITS
    ly
    0.28
    ogs
    0.27
    axter
    0.26
     young
    0.26
    .setSelection
    0.25
    jamin
    0.25
    SCP
    0.24
    utral
    0.24
     mutually
    0.24
    =?,
    0.23
    Activations Density 0.180%

    No Known Activations