© 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. 33281
    Prev
    Next
    INDEX
    Explanations

    stakes are

    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
    ени
    -0.10
    agli
    -0.09
     interstate
    -0.09
    åİŁä¾Ĩ
    -0.09
    elm
    -0.09
    åİŁæĿ¥
    -0.09
    èĩªè§ī
    -0.08
    åĥĸ
    -0.08
    çİ»çĴĥ
    -0.08
    åī¯ä¸»å¸Ń
    -0.08
    POSITIVE LOGITS
    åħ³ä¹İ
    0.16
    äºĭåħ³
    0.16
    æĪIJè´¥
    0.13
    æ¶īåıĬåĪ°
    0.11
    çļĦéĩįè¦ģæĢ§
    0.11
    çĶŁæŃ»
    0.11
     stakes
    0.11
    æĢ§åij½
    0.11
    æĶ¸
    0.11
    èĩ³åħ³éĩįè¦ģ
    0.10
    Activations Density 0.087%

    No Known Activations