© 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. 21797
    Prev
    Next
    INDEX
    Explanations

    molding and molding variations

    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
    OrNull
    -0.09
    ç©°
    -0.08
    éļľ
    -0.08
    nen
    -0.08
    èĮ«èĮ«
    -0.08
    AIL
    -0.08
     оÑĤмеÑĤ
    -0.08
    еÑĩен
    -0.08
    ially
    -0.08
    iating
    -0.08
    POSITIVE LOGITS
    ovan
    0.12
    çĬĦ
    0.10
    ering
    0.10
    eller
    0.10
    íĭĢ
    0.09
    .expires
    0.09
    ULAR
    0.09
     Caldwell
    0.09
    éļ¶å±ŀ
    0.09
    í
    0.09
    Activations Density 0.027%

    No Known Activations