© 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. 2355
    Prev
    Next
    INDEX
    Explanations

    contents of packages

    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
    åı£å¤´
    -0.09
    EDGE
    -0.09
    èĤ©è´Ł
    -0.09
    æµģä¼ł
    -0.09
    åĨ°ç®±
    -0.08
     refrigerator
    -0.08
    åĬŁèĥ½æĢ§
    -0.08
    Specifier
    -0.08
    èħ¹éĥ¨
    -0.08
    åŀĥåľ¾æ¡¶
    -0.08
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.26
    è¿Ľåİ»
    0.16
    Inside
    0.16
     Inside
    0.15
    inside
    0.15
     inside
    0.15
    éĩĮéĿ¢
    0.14
     therein
    0.13
    _inside
    0.13
     внÑĥÑĤÑĢи
    0.13
    Activations Density 0.185%

    No Known Activations