© 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. 62007
    Prev
    Next
    INDEX
    Explanations

    walked out/into/around/up/down/away

    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
    é«»
    -0.11
    åijĺ
    -0.10
    обÑĢа
    -0.10
    ECTOR
    -0.10
    OptionsResolver
    -0.10
    æ±°
    -0.10
     Scr
    -0.10
    æĢ§çĸ¾çĹħ
    -0.10
    culo
    -0.09
    缸å¤Ħ
    -0.09
    POSITIVE LOGITS
     walk
    0.08
    angel
    0.08
    åľ¨æİ¥åıĹ
    0.08
     Walk
    0.07
    _until
    0.07
     Walking
    0.07
    就被
    0.07
    akes
    0.07
    .walk
    0.07
    aps
    0.07
    Activations Density 0.022%

    No Known Activations