© 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. 37728
    Prev
    Next
    INDEX
    Explanations

    marrow transplant and stem cell transplantation

    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
     Barb
    -0.09
    ÑħваÑĤ
    -0.09
    夫
    -0.08
    èĢģåŃIJ
    -0.08
    èĢģå¹´
    -0.08
    çĿ½
    -0.08
    RAND
    -0.08
     $?
    -0.08
     occult
    -0.08
    çĶŁäº§åĬĽ
    -0.08
    POSITIVE LOGITS
    ç½ķè§ģ
    0.12
    æķijåĬ©
    0.11
    çĪ±å¿ĥ
    0.11
     nghá»ĭ
    0.10
    benef
    0.10
    ç¾ļ
    0.09
    çĹħæĪ¿
    0.09
    åĵªå®¶
    0.09
    æī¶
    0.09
    æĹ¶è¡¨ç¤º
    0.09
    Activations Density 0.067%

    No Known Activations