© 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. 22351
    Prev
    Next
    INDEX
    Explanations

    names and titles followed by common words

    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
    åĶ¾
    -0.10
     OPTIONAL
    -0.09
    åħ³æ³¨åº¦
    -0.09
    è´¨
    -0.08
    éģ¥
    -0.08
    éĢĢ
    -0.08
    æ¤Ł
    -0.08
    жи
    -0.08
    大å®Ĺ
    -0.08
    å¾Īä¹ħ
    -0.08
    POSITIVE LOGITS
    带头
    0.09
    å®Ľ
    0.09
    å°¤åħ¶
    0.09
    å½ķ
    0.09
     davon
    0.08
    èĮĥ
    0.08
    åıł
    0.08
    _ls
    0.08
    ÑĤÑĮ
    0.08
     Barg
    0.08
    Activations Density 0.090%

    No Known Activations