© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36796
    Prev
    Next
    INDEX
    Explanations

    deadly things

    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
    ity
    -0.12
    æŃ£å½ĵ
    -0.11
    ality
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    çľ¼è§Ĵ
    -0.09
    land
    -0.09
    ftware
    -0.09
    aries
    -0.09
    nist
    -0.08
    entication
    -0.08
    POSITIVE LOGITS
    3
    0.09
    ее
    0.09
    2
    0.09
    veau
    0.09
    odule
    0.09
    4
    0.09
    oding
    0.08
    9
    0.08
    5
    0.08
    0
    0.08
    Activations Density 0.011%

    No Known Activations