© 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. 51378
    Prev
    Next
    INDEX
    Explanations

    ben names

    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
    åĺī宾
    -0.10
    edList
    -0.10
    ÑĩаÑĤ
    -0.09
    matic
    -0.09
    æı½
    -0.09
    ment
    -0.09
    äºijéĽĨ
    -0.08
    asan
    -0.08
    umm
    -0.08
    er
    -0.08
    POSITIVE LOGITS
    jamin
    0.15
    itez
    0.11
    ning
    0.10
    åŃIJéĩĮ
    0.10
    oit
    0.10
    Ñģ
    0.09
    bers
    0.09
    åĵ®
    0.09
    ties
    0.09
    ãģ¦ãĤĤ
    0.09
    Activations Density 0.024%

    No Known Activations