© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36085
    Prev
    Next
    INDEX
    Explanations

    software and code licenses

    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
    éĻĦ
    -0.09
    åĢ¬
    -0.08
    airy
    -0.08
     sno
    -0.08
    rig
    -0.08
    åĺ»åĺ»
    -0.08
    çĤĴä½ľ
    -0.08
    åıĸè¯ģ
    -0.08
    èĩ³å°ij
    -0.08
    ILT
    -0.08
    POSITIVE LOGITS
    ÙĦاء
    0.09
    .fi
    0.09
    æħĮ
    0.09
    agli
    0.09
     ÑĢа
    0.09
    entes
    0.09
    onis
    0.09
    建åĨĽ
    0.09
    inel
    0.08
    åį§
    0.08
    Activations Density 0.141%

    No Known Activations