© 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. 20263
    Prev
    Next
    INDEX
    Explanations

    speculation and guesses

    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
    åĸ»
    -0.10
    ORM
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    è®©æĽ´å¤ļ
    -0.09
    ç»ĵæŀĦè°ĥæķ´
    -0.09
    æ·¹
    -0.09
    elter
    -0.09
    深交
    -0.08
    æŃ£å®Ĺ
    -0.08
    sit
    -0.08
    POSITIVE LOGITS
    çĮľæµĭ
    0.29
    æݨæµĭ
    0.23
    çĮľæĥ³
    0.22
    çĮľ
    0.20
    æı£
    0.19
     speculation
    0.17
     guess
    0.16
    guess
    0.16
    Guess
    0.16
     guesses
    0.14
    Activations Density 0.072%

    No Known Activations