© 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. 32077
    Prev
    Next
    INDEX
    Explanations

    website installation

    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
    .Rec
    -0.10
    _('
    -0.09
    .returnValue
    -0.08
    anine
    -0.08
    epy
    -0.08
     recru
    -0.08
    å»ĭ
    -0.08
    acr
    -0.08
    erek
    -0.08
    .Criteria
    -0.08
    POSITIVE LOGITS
    orney
    0.10
    ç«ĻçĤ¹
    0.10
    icz
    0.09
    åıĻäºĭ
    0.08
    åIJĮå¿ĥ
    0.08
    ä½Ĺ
    0.08
    ç¼Ģ
    0.08
    ä¸Ģç«Ļ
    0.08
    ç¼Ķ
    0.08
    ä»
    0.08
    Activations Density 0.252%

    No Known Activations