© 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. 54162
    Prev
    Next
    INDEX
    Explanations

    Caesar and variations

    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
    onder
    -0.10
    /books
    -0.09
    ridge
    -0.09
    jection
    -0.08
    çİĻ
    -0.08
    ledge
    -0.08
    ÑĢÑı
    -0.08
    اÙĥ
    -0.08
    omen
    -0.08
    ï¾ŀ
    -0.08
    POSITIVE LOGITS
    istic
    0.13
    ðŁı»
    0.10
    wig
    0.09
    ISTIC
    0.09
    ians
    0.09
    éĻĽ
    0.09
    itate
    0.09
    uate
    0.09
    å«Ķ
    0.09
    owed
    0.09
    Activations Density 0.014%

    No Known Activations