© 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. 49940
    Prev
    Next
    INDEX
    Explanations

    open source

    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
     forthcoming
    -0.09
    sing
    -0.09
    /her
    -0.08
    uba
    -0.08
    utom
    -0.08
    som
    -0.08
    alog
    -0.08
    istic
    -0.08
    olib
    -0.08
    ikan
    -0.08
    POSITIVE LOGITS
    weathermap
    0.15
    -minded
    0.14
    -ended
    0.14
    -hearted
    0.12
    eing
    0.12
     minded
    0.11
    prising
    0.11
    à¹ĥà¸Ī
    0.11
    èĩªå¦Ĥ
    0.11
    äºĨä¸Ģ
    0.10
    Activations Density 0.095%

    No Known Activations