© 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. 49463
    Prev
    Next
    INDEX
    Explanations

    existence and presence

    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
    åĩĨ
    -0.09
     mist
    -0.09
    ä¸įåłª
    -0.08
    èĩªå¾ĭ
    -0.08
     Gib
    -0.08
    åħ«å¤§
    -0.08
    NAL
    -0.08
    ÙĨز
    -0.08
     Burb
    -0.08
    追éļı
    -0.08
    POSITIVE LOGITS
    çļĦåŃĺåľ¨
    0.19
     existence
    0.16
     exist
    0.14
    existence
    0.13
    Exist
    0.13
    è¿Ļä¹Ī
    0.13
     presence
    0.12
    presence
    0.12
     exists
    0.12
     Exists
    0.12
    Activations Density 0.083%

    No Known Activations