© 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. 18064
    Prev
    Next
    INDEX
    Explanations

    abnormalities

    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
    åĿıäºĭ
    -0.10
    borne
    -0.10
    èĴĻ
    -0.10
    æĥ³åĬŀæ³ķ
    -0.10
    æ¯ĶèµĽä¸Ń
    -0.09
    dle
    -0.09
    延误
    -0.09
    æįĭ
    -0.09
    åŃļ
    -0.09
    åĨĴ
    -0.09
    POSITIVE LOGITS
    ity
    0.15
    -minded
    0.13
    ities
    0.12
    ä¹ĭå¤Ħ
    0.11
    ITIES
    0.10
     minded
    0.09
    ties
    0.09
    гоÑĢод
    0.09
     gamm
    0.08
    è°ģèĥ½
    0.08
    Activations Density 0.074%

    No Known Activations