© 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. 32543
    Prev
    Next
    INDEX
    Explanations

    response to

    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
    åĨ¤
    -0.10
    igan
    -0.09
    ä¸Ģçľ¼
    -0.09
    0
    -0.09
    åıijéŁ³
    -0.08
    1
    -0.08
    9
    -0.08
    éĺ´éĺ³
    -0.08
    ä¸Ńåľº
    -0.08
    8
    -0.08
    POSITIVE LOGITS
    /response
    0.11
    积æŀģåĵįåºĶ
    0.11
    åĵįåºĶ
    0.10
    pone
    0.10
    wl
    0.09
    wards
    0.09
    åıįåĵį
    0.09
    (Response
    0.09
    ivate
    0.09
     конÑģÑĤÑĢÑĥкÑĨи
    0.08
    Activations Density 0.072%

    No Known Activations