© 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. 57222
    Prev
    Next
    INDEX
    Explanations

    Howard

    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
    ðŁı»
    -0.10
    bones
    -0.10
    mate
    -0.09
    ertil
    -0.09
    ðŁı¼
    -0.09
    SizePolicy
    -0.09
    mates
    -0.08
    ifying
    -0.08
    äºĨä¸įå°ij
    -0.08
    ï¸
    -0.08
    POSITIVE LOGITS
    thon
    0.12
    å¹³æ°ij
    0.10
    aret
    0.09
    åħ¶ä»ĸ人
    0.09
    иÑģÑĤ
    0.09
    تÙĪ
    0.09
    plet
    0.09
    å·¥ä½ľèĢħ
    0.09
    ances
    0.09
    care
    0.09
    Activations Density 0.068%

    No Known Activations