© 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. 22491
    Prev
    Next
    INDEX
    Explanations

    city film festival

    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
    èĨ³
    -0.10
    ta
    -0.10
    ty
    -0.10
    ters
    -0.09
    typ
    -0.09
    ter
    -0.09
    tt
    -0.09
    触
    -0.09
    å¸ĥ
    -0.08
    ãĥĥ
    -0.08
    POSITIVE LOGITS
    خت
    0.10
    鼩
    0.09
    éĤ¾
    0.09
    æݥ管
    0.08
    ald
    0.08
    éĿĴå±±
    0.08
    @js
    0.08
    elter
    0.08
    éĺ²åį«
    0.08
    :def
    0.08
    Activations Density 0.002%

    No Known Activations