© 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. 38892
    Prev
    Next
    INDEX
    Explanations

    scientific articles

    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
     cookies
    -0.28
     SSR
    -0.27
     BATCH
    -0.25
    ç»ĪçĶŁ
    -0.24
    代çIJĨ人
    -0.23
     affirmation
    -0.23
     advise
    -0.23
    å®ĮåĸĦçļĦ
    -0.23
     agreeing
    -0.23
     affinity
    -0.23
    POSITIVE LOGITS
    ial
    0.34
    imal
    0.30
    ystone
    0.29
    ity
    0.29
    til
    0.28
    iry
    0.28
    ilded
    0.28
    ially
    0.28
    osex
    0.28
    td
    0.28
    Activations Density 4.369%

    No Known Activations