© 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. 31515
    Prev
    Next
    INDEX
    Explanations

    give clues to tell a story

    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
    åıijçĶŁåľ¨
    -0.10
    èµ·ãģį
    -0.09
    еÑģÑĤв
    -0.08
    æĿ¡ä¾ĭ
    -0.08
    çŁ³çģ°
    -0.08
    çĶļ
    -0.08
    ima
    -0.08
    .central
    -0.08
    庳
    -0.08
    ennon
    -0.08
    POSITIVE LOGITS
    æ³Ħéľ²
    0.13
    è¿Ļä¸ĢçĤ¹
    0.12
     clue
    0.12
     clues
    0.12
    éĢıéľ²
    0.12
    å±IJ
    0.11
    æ´
    0.10
     betray
    0.10
    线索
    0.10
     betrayed
    0.10
    Activations Density 0.038%

    No Known Activations