© 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. 38919
    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
    Document
    -0.27
    è´¨
    -0.26
    (Func
    -0.26
    Äħż
    -0.25
    AF
    -0.25
    (!_
    -0.25
    ase
    -0.24
    è°¢è°¢ä½ł
    -0.24
    ;}č↵
    -0.24
    berger
    -0.24
    POSITIVE LOGITS
    erator
    0.32
    äºĨä¸Ģéģį
    0.26
    quisites
    0.26
     lif
    0.26
     Staten
    0.26
    åįģåĪĨéĴŁ
    0.25
    éĴŁ
    0.25
    licant
    0.25
     differential
    0.24
     повÑĤоÑĢ
    0.24
    Activations Density 7.968%

    No Known Activations

    This feature has no known activations.