© 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. 30752
    Prev
    Next
    INDEX
    Explanations

    resistance and sensitivity

    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
    å®ģ
    -0.09
     incent
    -0.09
    èĢĥè¯Ħ
    -0.09
    å¡«åħħ
    -0.09
    ä¸įæĺ¯ä¸Ģ个
    -0.09
    åĸĿéħĴ
    -0.08
    å®ģåİ¿
    -0.08
    yle
    -0.08
     seek
    -0.08
    ç¾Ķ
    -0.08
    POSITIVE LOGITS
    æĬĹæĭĴ
    0.10
    åIJ¬åıĸ
    0.10
    è®°å¾Ĺ
    0.10
    éĺ»åĬĽ
    0.09
    prite
    0.09
    è¡Ĺä¸Ĭ
    0.09
    lift
    0.09
    éĺ²æĻĴ
    0.09
     resistance
    0.09
    äºĮåįģåĽĽ
    0.09
    Activations Density 0.233%

    No Known Activations