© 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. 54936
    Prev
    Next
    INDEX
    Explanations

    distribution modification

    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
    æŶè£ħ
    -0.09
    wards
    -0.09
    epar
    -0.09
    RESS
    -0.08
    å¹³åı°ä¸Ĭ
    -0.08
    éĢģè´§
    -0.08
    auty
    -0.08
    éĤ£ä¸Ģ
    -0.08
    _FM
    -0.08
    ackson
    -0.08
    POSITIVE LOGITS
     regard
    0.20
     regards
    0.19
    stood
    0.13
    outh
    0.12
     vengeance
    0.12
     impunity
    0.11
    åħ¶ä»ĸ人
    0.11
    holds
    0.11
    standing
    0.10
     respect
    0.10
    Activations Density 1.026%

    No Known Activations