© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    both ... and

    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
    åıĪ称
    -0.10
    å±Ĥå±Ĥ
    -0.10
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
     мил
    -0.09
    движ
    -0.09
    çĨĬçĮ«
    -0.09
    æŀ°
    -0.08
    çĺ¤
    -0.08
    heads
    -0.08
    urb
    -0.08
    POSITIVE LOGITS
     obvious
    0.09
    åĨħåľ¨
    0.09
    åľ¨å®¶éĩĮ
    0.08
    以åIJİ
    0.08
    å®īæħ°
    0.08
     Metallic
    0.08
    为åħ¶
    0.08
    lod
    0.08
    åľ¨æİ¥åıĹ
    0.08
    loc
    0.08
    Activations Density 0.045%

    No Known Activations