© 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. 4125
    Prev
    Next
    INDEX
    Explanations

    claims and billing statements

    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
    Legacy
    -0.09
    约è°Ī
    -0.09
    ennon
    -0.09
    æıIJéĹ®
    -0.09
    æĦŁæģ©
    -0.08
     Lol
    -0.08
    åİĨå¹´
    -0.08
    Ñĭми
    -0.08
     pap
    -0.08
    erton
    -0.08
    POSITIVE LOGITS
    宣称
    0.20
    å®£ä¼ł
    0.18
    声称
    0.17
     promised
    0.15
     promises
    0.14
    æī¿è¯º
    0.14
     claim
    0.14
    åı·ç§°
    0.14
     claims
    0.14
    claim
    0.14
    Activations Density 0.133%

    No Known Activations