© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    unto words

    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
    nt
    -0.10
    éĹªçĶµ
    -0.09
    æģ°æģ°
    -0.09
    erry
    -0.08
    girl
    -0.08
    วà¸Ļ
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    rooms
    -0.08
    æ±ķ
    -0.08
    ician
    -0.08
    POSITIVE LOGITS
    gether
    0.11
    itial
    0.10
    æ·±å¤Ħ
    0.09
    èĢģçĻ¾å§ĵ
    0.09
    åIJĦ个çݯèĬĤ
    0.09
    stüt
    0.09
    ests
    0.09
    VES
    0.09
    erner
    0.08
    ÑĤвоÑĢ
    0.08
    Activations Density 0.009%

    No Known Activations