© 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. 38609
    Prev
    Next
    INDEX
    Explanations

    contains "ace"

    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
    Negative Logits
    oir
    -0.28
    æıIJè´¨
    -0.27
     Shia
    -0.27
     discrim
    -0.26
     sporting
    -0.26
     Sylvia
    -0.25
     décor
    -0.25
    okin
    -0.25
     todd
    -0.24
    Spoiler
    -0.24
    POSITIVE LOGITS
    aces
    0.35
    iance
    0.35
    ace
    0.35
    ANCE
    0.34
    iances
    0.34
    ance
    0.32
    auce
    0.32
    af
    0.31
    av
    0.29
    ouce
    0.29
    Activations Density 6.095%

    No Known Activations