© 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. 4669
    Prev
    Next
    INDEX
    Explanations

    wrong with this

    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
    åıĸå¾Ĺ
    -0.10
    çĵ
    -0.09
    eral
    -0.09
     Pace
    -0.09
    Peripheral
    -0.08
    äºij
    -0.08
    д
    -0.08
    gis
    -0.08
    osi
    -0.08
    æį§
    -0.08
    POSITIVE LOGITS
    æ¯ĽçĹħ
    0.13
    çİĭåŃIJ
    0.10
    æ®ĸ
    0.10
     sickness
    0.09
     wrong
    0.09
    头èĦij
    0.09
     elit
    0.09
    åĸľæ¬¢åIJĥ
    0.09
    两çĤ¹
    0.09
    çĭ¬çī¹
    0.09
    Activations Density 0.034%

    No Known Activations