© 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. 10938
    Prev
    Next
    INDEX
    Explanations

    blood and related concepts

    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
    çĭIJ
    -0.10
    æ°ĶåĢĻåıĺåĮĸ
    -0.09
    åıijå±ķçIJĨ念
    -0.09
    ç¾İå¾·
    -0.09
    è¶ħé¢Ŀ
    -0.09
    çħĮ
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.09
     пÑĢедмеÑĤ
    -0.09
    uffer
    -0.08
    annis
    -0.08
    POSITIVE LOGITS
    è¡Ģ
    0.13
    åī²
    0.11
    é²ľè¡Ģ
    0.11
    è¡Ģèħ¥
    0.10
    shed
    0.10
    -blood
    0.09
    blood
    0.09
    Blood
    0.09
    è¡·
    0.09
    stone
    0.09
    Activations Density 0.018%

    No Known Activations