© 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. 53481
    Prev
    Next
    INDEX
    Explanations

    Klein or oligonucleotide sequences

    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
    unge
    -0.10
    åħħæ²Ľ
    -0.10
    amel
    -0.09
    fully
    -0.09
    æľŁéĻIJ
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    icular
    -0.08
    æĢ§çĸ¾çĹħ
    -0.08
    eer
    -0.08
    outh
    -0.08
    POSITIVE LOGITS
    -minded
    0.14
    ened
    0.12
     minded
    0.11
    -hearted
    0.11
    -sized
    0.11
    wares
    0.10
    ening
    0.10
    ens
    0.10
    ewood
    0.10
    /small
    0.10
    Activations Density 0.023%

    No Known Activations