© 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. 52780
    Prev
    Next
    INDEX
    Explanations

    gossip stories

    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
    igh
    -0.10
    noch
    -0.09
    igit
    -0.09
    åºŁå¼ĥ
    -0.08
    aters
    -0.08
    å¹ħ
    -0.08
     Brotherhood
    -0.08
    ality
    -0.08
    amura
    -0.08
    itud
    -0.08
    POSITIVE LOGITS
    ingly
    0.11
    çĶŁæ¶¯
    0.10
    轶
    0.09
    åĹij
    0.09
    gram
    0.09
    å¸ļ
    0.09
    elon
    0.09
    antium
    0.09
    è§ļ
    0.08
     Rath
    0.08
    Activations Density 0.002%

    No Known Activations