© 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. 33-TRANSCODER-HP
    7. 52679
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rev
    -0.28
    ä½ķ
    -0.28
    éĢı
    -0.28
     derog
    -0.27
    efully
    -0.26
    holding
    -0.26
    mant
    -0.26
    rot
    -0.25
     pl
    -0.25
     Og
    -0.25
    POSITIVE LOGITS
    çĬ¯
    0.27
    struk
    0.27
    nerRadius
    0.27
    ABCDEFGHI
    0.25
     CLAIM
    0.25
     faculties
    0.24
    UIT
    0.23
    antz
    0.23
    åijĹ
    0.23
    loff
    0.23
    Activations Density 0.006%

    No Known Activations