© 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. 19913
    Prev
    Next
    INDEX
    Explanations

    realistic and believable descriptions

    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
    isia
    -0.09
    ì¤Ħ
    -0.09
    ä¼ĹæīĢ
    -0.09
    iy
    -0.09
    åľ¨å½ĵåľ°
    -0.09
    EntityType
    -0.09
    å±Ĥåĩº
    -0.09
    妮
    -0.09
    ä¸Ģå¹´å¤ļ
    -0.09
    æĹłæķ°æ¬¡
    -0.09
    POSITIVE LOGITS
    éĢ¼
    0.15
     realistic
    0.12
     realism
    0.10
    å½¹
    0.10
    istic
    0.09
    羣å®ŀæĢ§
    0.09
     Authority
    0.09
    羣å®ŀ
    0.09
    æ³Ħ
    0.08
    authority
    0.08
    Activations Density 0.051%

    No Known Activations