© 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. 39191
    Prev
    Next
    INDEX
    Explanations

    hack-and-slash

    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
    åĺŁ
    -0.09
    è¢į
    -0.09
    缸åħ³åĨħ容
    -0.09
    æ¿Ĵ临
    -0.09
    é¦ĸéĢī
    -0.08
    éĽĨè£ħ
    -0.08
    ä»İä¸Ń
    -0.08
    iming
    -0.08
    çĶļèĩ³è¿ŀ
    -0.08
    çĶļèĩ³
    -0.08
    POSITIVE LOGITS
    alysis
    0.10
    alink
    0.10
    alog
    0.10
    бол
    0.09
    thew
    0.09
    burger
    0.09
    彩
    0.08
    .rpm
    0.08
    alu
    0.08
    trys
    0.08
    Activations Density 0.077%

    No Known Activations