© 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. 5046
    Prev
    Next
    INDEX
    Explanations

    Super, followed by specific words

    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
    AndUpdate
    -0.10
    soever
    -0.10
    rpc
    -0.09
    aters
    -0.09
    å§Ķåī¯ä¹¦è®°
    -0.09
    ãģŁãĤģãģ«
    -0.09
    sel
    -0.09
    rin
    -0.09
    quarters
    -0.08
    åĽŀäºĭ
    -0.08
    POSITIVE LOGITS
    -minded
    0.16
    intendent
    0.14
    cede
    0.13
    IOR
    0.13
    ior
    0.13
    ity
    0.13
    ../../../
    0.13
    iors
    0.13
    stit
    0.11
    charged
    0.11
    Activations Density 0.069%

    No Known Activations