© 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. 61740
    Prev
    Next
    INDEX
    Explanations

    another or further quantity

    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
    åľºåIJĪ
    -0.09
    åĪ©çĶ¨çİĩ
    -0.09
    éĵĿ
    -0.09
    次æķ°
    -0.08
     окÑĢÑĥ
    -0.08
     Stern
    -0.08
    大大å°ıå°ı
    -0.08
    å¹Ķ
    -0.08
    ä¸į说
    -0.08
    agen
    -0.08
    POSITIVE LOGITS
    ä¸Ģå°ı
    0.12
    olec
    0.10
    ä¸Ģ段
    0.10
    å°ij许
    0.09
    åĩłçĻ¾
    0.09
    egin
    0.09
    ä¸īåĪĨ
    0.09
    viron
    0.09
    _Var
    0.09
    ä¸īåĪĨä¹ĭä¸Ģ
    0.09
    Activations Density 0.076%

    No Known Activations