© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62933
    Prev
    Next
    INDEX
    Explanations

    soundtrack or score

    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
    çī¯
    -0.09
    路段
    -0.08
    禧
    -0.08
    Mex
    -0.08
    adiator
    -0.08
    ance
    -0.08
    anged
    -0.08
    ç»ıæµİä½ĵ
    -0.08
     flakes
    -0.08
     heck
    -0.08
    POSITIVE LOGITS
    è¿·
    0.10
    çĶ±æѤ
    0.10
    à¸ķร
    0.09
    rop
    0.09
    ted
    0.09
    ива
    0.09
    ount
    0.09
    lots
    0.08
    _FRE
    0.08
    _hover
    0.08
    Activations Density 0.007%

    No Known Activations