© 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. 53998
    Prev
    Next
    INDEX
    Explanations

    imm- following 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
    lette
    -0.11
    roud
    -0.10
    pus
    -0.10
    leton
    -0.10
    ird
    -0.10
    dre
    -0.10
    æīĢæľī人éĥ½
    -0.10
    Ñģад
    -0.09
    ermen
    -0.09
    omba
    -0.09
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.13
    EDIATE
    0.11
    agine
    0.11
    agini
    0.10
    eses
    0.09
    è¾ľ
    0.09
    aries
    0.09
    å±ıéļľ
    0.09
    ovable
    0.08
    igrant
    0.08
    Activations Density 0.042%

    No Known Activations