© 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. 61989
    Prev
    Next
    INDEX
    Explanations

    reckon, reckoning, reckless

    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
    ŀ
    -0.10
    athing
    -0.10
    ying
    -0.09
    ularity
    -0.09
    isu
    -0.09
    okie
    -0.09
    inas
    -0.08
    reh
    -0.08
    .FONT
    -0.08
    ÅĤo
    -0.08
    POSITIVE LOGITS
    å°¼äºļ
    0.10
    iful
    0.10
    ably
    0.10
    oning
    0.10
    åİŁæłĩé¢ĺ
    0.09
    enance
    0.09
    ä¸įæ¸ħ
    0.09
    ·
    0.09
    ingly
    0.09
    ×ķת
    0.09
    Activations Density 0.004%

    No Known Activations