© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36953
    Prev
    Next
    INDEX
    Explanations

    trails and paths

    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
    çĺª
    -0.09
    æİł
    -0.09
    pty
    -0.09
    æ³±
    -0.09
    ally
    -0.09
    oko
    -0.09
    æłª
    -0.08
    PRI
    -0.08
    ptive
    -0.08
    ĥģ
    -0.08
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.10
     VOID
    0.10
    è¥¿çº¢æŁ¿
    0.09
    çĩļ
    0.09
    梦幻
    0.09
    once
    0.08
    mind
    0.08
    éĢłçº¸
    0.08
    è¹
    0.08
    大çģ«
    0.08
    Activations Density 0.010%

    No Known Activations