© 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. 38897
    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
    åIJĥäºĨ
    -0.26
    æ¯į
    -0.25
    çļĦéĤ£ä¸ª
    -0.25
    çĬį
    -0.25
     ourselves
    -0.25
    åݿ级
    -0.25
    ly
    -0.24
    ündig
    -0.24
    欧å¼ı
    -0.24
    å±ħ
    -0.24
    POSITIVE LOGITS
    noc
    0.28
    ä»İä¸ļ
    0.26
     competence
    0.25
     enrol
    0.25
    éļı
    0.24
    ilor
    0.24
    ftware
    0.24
    afa
    0.24
    illis
    0.24
    edback
    0.24
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.