© 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. 61244
    Prev
    Next
    INDEX
    Explanations

    places or states of being

    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
    еÑģп
    -0.09
    æ¶ĪåĮĸ
    -0.09
    å¹¿æ³Ľ
    -0.09
    ç»
    -0.08
    amba
    -0.08
    å¼ĵ
    -0.08
    emes
    -0.08
    _DD
    -0.08
    annie
    -0.08
    åħ¨ç¨ĭ
    -0.08
    POSITIVE LOGITS
    åľ°å¤Ħ
    0.12
    åģıè¿ľ
    0.11
    åı¯æĥ³èĢĮçŁ¥
    0.10
    åıijè¾¾
    0.10
    ç¹ģèį£
    0.10
    çł´æįŁ
    0.09
    eliness
    0.09
    éĻĭ
    0.09
    没éĴ±
    0.09
    æĹłæ¯Ķ
    0.09
    Activations Density 0.073%

    No Known Activations