© 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. 3654
    Prev
    Next
    INDEX
    Explanations

    pricing and availability

    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
    åħ¬åħ±èµĦæºIJ
    -0.09
    èݲ
    -0.08
    Ñĥма
    -0.08
    .comm
    -0.08
     archives
    -0.08
    ç»Ī
    -0.08
    çĭ¸
    -0.08
     Claudia
    -0.08
    ASCII
    -0.08
    ÑĮÑıн
    -0.07
    POSITIVE LOGITS
     Availability
    0.12
    æı©
    0.11
    ecure
    0.10
     Hof
    0.10
     availability
    0.10
    å¾·æĭī
    0.09
    pri
    0.09
    ÈĽi
    0.09
    ç¬ij声
    0.09
    _OID
    0.09
    Activations Density 0.014%

    No Known Activations