© 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. 55373
    Prev
    Next
    INDEX
    Explanations

    adding content or items

    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
    强çĥĪ
    -0.11
    ingly
    -0.10
     же
    -0.09
    بÙĪÙĥ
    -0.09
    uality
    -0.09
    дж
    -0.09
    _CREAT
    -0.09
    nement
    -0.09
    åģ»
    -0.09
    iro
    -0.09
    POSITIVE LOGITS
    itionally
    0.18
    endum
    0.18
    resse
    0.18
    ITIONAL
    0.17
    OrUpdate
    0.17
    ition
    0.16
    itions
    0.16
    -ons
    0.15
    itional
    0.15
    enda
    0.15
    Activations Density 0.110%

    No Known Activations