© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39411
    Prev
    Next
    INDEX
    Explanations

    The

    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
    oplay
    -0.26
    é«ĺé¢ij
    -0.25
    æĺł
    -0.25
    oho
    -0.24
     quanto
    -0.24
    UTO
    -0.24
    oyo
    -0.23
     assum
    -0.23
    loff
    -0.23
    æŃĩ
    -0.23
    POSITIVE LOGITS
     Treasure
    0.29
     P
    0.29
     Football
    0.28
     Saga
    0.28
     W
    0.28
     Middle
    0.27
    berries
    0.27
     Job
    0.27
     Career
    0.27
     Cow
    0.27
    Activations Density 0.230%

    No Known Activations