© 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. 21709
    Prev
    Next
    INDEX
    Explanations

    threaten one

    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
    å«īå¦Ĵ
    -0.12
    å¦Ĵ
    -0.10
    гад
    -0.09
    å«ī
    -0.09
    pcb
    -0.08
    åĪ»èĭ¦
    -0.08
    é¾Ĭ
    -0.08
    rats
    -0.08
    /oauth
    -0.08
    åĬłæĮģ
    -0.08
    POSITIVE LOGITS
    èĩªçĶ±è´¸æĺĵ
    0.12
     liberty
    0.12
    åıįæĬĹ
    0.10
    人æĢ§åĮĸ
    0.09
    èĩªçĶ±
    0.09
    å®īæĬļ
    0.09
    çĺ«
    0.09
    èī¯
    0.09
    rang
    0.09
    éĻªçĿĢ
    0.09
    Activations Density 0.276%

    No Known Activations