© 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. 38914
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    UTILITY
    -0.29
     slept
    -0.28
    转åĮĸ
    -0.27
    atee
    -0.26
     concession
    -0.25
    é£İéĻ©
    -0.25
     sincerity
    -0.25
    utility
    -0.25
     Slee
    -0.24
    styl
    -0.24
    POSITIVE LOGITS
    ix
    0.27
    ipt
    0.27
    äºij
    0.26
    庶
    0.25
    _fu
    0.24
    麻
    0.24
    _filenames
    0.24
    cms
    0.24
    å¼Ģå¿ĥ
    0.24
     downloadable
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.