© 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. 40431
    Prev
    Next
    INDEX
    Explanations

    Code and technical texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -ln
    -0.28
    åĤį
    -0.26
    æķ°åŃĹåĮĸ
    -0.25
    åİŁæłĩé¢ĺ
    -0.25
    å±ĭ
    -0.24
    ähl
    -0.23
     flames
    -0.23
    leigh
    -0.23
    arg
    -0.23
    ulis
    -0.22
    POSITIVE LOGITS
    a
    0.32
    opers
    0.31
    op
    0.31
    Op
    0.31
    OP
    0.31
    ailable
    0.30
    ople
    0.30
    opes
    0.29
    æĦıè§ģåıįé¦Ī
    0.28
    rap
    0.28
    Activations Density 0.377%

    No Known Activations