© 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. 54302
    Prev
    Next
    INDEX
    Explanations

    register and user details

    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
    泺
    -0.09
    rine
    -0.09
    å®Ī
    -0.09
     rental
    -0.09
    æĥłæ°ij
    -0.09
    mium
    -0.08
    .atomic
    -0.08
    ropolis
    -0.08
    jective
    -0.08
    佬
    -0.08
    POSITIVE LOGITS
    (Register
    0.14
    (register
    0.12
    çĻ»è®°
    0.11
    _unregister
    0.11
     register
    0.10
    注åĨĮ
    0.10
     Register
    0.10
    etimes
    0.10
     regist
    0.10
    register
    0.10
    Activations Density 0.102%

    No Known Activations