© 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. 39946
    Prev
    Next
    INDEX
    Explanations

    C

    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
    ä¼łç»Ł
    -0.27
    èĢģ大
    -0.27
    åľ¨å®¶
    -0.26
     APC
    -0.26
    å¦Ĥä½ķåİ»
    -0.25
    erts
    -0.25
    oug
    -0.25
    çľĭä»ĸ
    -0.24
     apoptosis
    -0.24
    ruc
    -0.24
    POSITIVE LOGITS
    å°Ħ
    0.26
    itur
    0.26
     troub
    0.24
    éħIJ
    0.24
     enc
    0.24
     correspond
    0.24
    bah
    0.24
    æıIJä¾Ľ
    0.24
     bás
    0.23
    æłĩæĺİ
    0.23
    Activations Density 75.703%

    No Known Activations