© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    AP news attribution

    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
    åı¯ä»¥è¯´
    -0.09
    çłĶåıijæĬķåħ¥
    -0.08
    inear
    -0.08
     pirate
    -0.08
    anova
    -0.08
    าะ
    -0.08
    客åİħ
    -0.08
    ÅĤad
    -0.08
    ä¸Ĭ次
    -0.08
    ار
    -0.07
    POSITIVE LOGITS
    ãģĤãĤĭ
    0.10
     cứu
    0.10
    duto
    0.09
    ignon
    0.09
    ocy
    0.09
    iction
    0.09
    èĩªå¦Ĥ
    0.09
    rema
    0.09
    usch
    0.08
    éĢµ
    0.08
    Activations Density 0.022%

    No Known Activations