© 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. 31194
    Prev
    Next
    INDEX
    Explanations

    pipeline descriptor

    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
    ening
    -0.12
    atives
    -0.10
    ened
    -0.10
    åĴIJ
    -0.09
    ÂŃt
    -0.09
     rÃłng
    -0.09
    enance
    -0.09
    ends
    -0.09
    est
    -0.09
    ORMAT
    -0.09
    POSITIVE LOGITS
    æѤåĪ»
    0.10
    ÑĢеÑģ
    0.10
    arity
    0.09
    onso
    0.09
    ç¬Ļ
    0.09
    åıijå±ķä¸Ń
    0.09
    大éŨ
    0.09
    ãģĤãĤĬãģ¾ãģĹãģŁ
    0.08
    é¹ķ
    0.08
    hip
    0.08
    Activations Density 0.010%

    No Known Activations