© 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. 21437
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    åijĢ
    -0.10
    æŃĥ
    -0.09
    çłº
    -0.09
    å°±åľ¨äºİ
    -0.09
    евиÑĩ
    -0.09
    åŃĺéĩı
    -0.09
    çĶŁæĢķ
    -0.09
    åħ¶å®ĥ
    -0.09
    交æİ¥
    -0.08
    ä¹IJæĦı
    -0.08
    POSITIVE LOGITS
    ÑĢажа
    0.08
     Jeans
    0.08
    braco
    0.08
    @param
    0.08
    roads
    0.08
    owned
    0.08
    _OD
    0.08
    autiful
    0.07
    emies
    0.07
    enas
    0.07
    Activations Density 0.143%

    No Known Activations