© 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. 33-TRANSCODER-HP
    7. 53638
    Prev
    Next
    INDEX
    Explanations

    Diet, feeding, scientific names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬å¼Ģåıij
    -0.30
    å±IJ
    -0.28
    身ä½ĵåģ¥åº·
    -0.27
    娱
    -0.25
    è··
    -0.25
    åĸĤ
    -0.25
    饲
    -0.24
    виÑĤ
    -0.24
     feeding
    -0.23
     <!--[
    -0.23
    POSITIVE LOGITS
    Principal
    0.30
    çĤ¹åįĬ
    0.28
     subs
    0.28
     Principal
    0.27
     Con
    0.27
    osaurs
    0.27
     rel
    0.27
    主è¦ģ
    0.26
     Conrad
    0.26
     principal
    0.26
    Activations Density 0.008%

    No Known Activations