© 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. 31196
    Prev
    Next
    INDEX
    Explanations

    Washington, D.C

    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
     chaining
    -0.09
    ATAR
    -0.09
    æı©
    -0.09
    LÄ°
    -0.09
    缸åĬ©
    -0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.09
    kes
    -0.09
    uely
    -0.09
    ıyla
    -0.09
    жи
    -0.09
    POSITIVE LOGITS
    -area
    0.09
    éĻĦè¿ijçļĦ
    0.09
    çĤ¸
    0.09
    ä¸Ģçīĩ
    0.09
    /or
    0.09
    éĻĦè¿ij
    0.08
    èĶĵ
    0.08
     shell
    0.08
    çŃīåľ°
    0.08
    urr
    0.08
    Activations Density 0.007%

    No Known Activations