© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50915
    Prev
    Next
    INDEX
    Explanations

    series, albums, plays, or periodicals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trá»įng
    -0.10
    rove
    -0.09
    åłķ
    -0.09
    arf
    -0.08
    èı°
    -0.08
    æĪĺ
    -0.08
    çĹķ
    -0.08
    æĺŁè¾°
    -0.08
    åĽłæŀľ
    -0.08
    opot
    -0.08
    POSITIVE LOGITS
    å¢ħ
    0.11
    ç«¥è¯Ŀ
    0.09
    .FILL
    0.09
    æĸ°é²ľ
    0.09
    èĢį
    0.09
    .toByteArray
    0.09
    éļİ
    0.08
    åĨĻåŃĹ
    0.08
     Coco
    0.08
    éĺ¶
    0.08
    Activations Density 0.006%

    No Known Activations