© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47591
    Prev
    Next
    INDEX
    Explanations

    SSH login failure

    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
    Negative Logits
    ä¸Ģè´¯
    -0.10
    æ¥ł
    -0.10
    涧
    -0.09
    idge
    -0.09
    éĢł
    -0.09
    ç½Ķ
    -0.09
    åĻĹ
    -0.08
    hes
    -0.08
    çģµ
    -0.08
    CCC
    -0.08
    POSITIVE LOGITS
    æĶ»åĩ»
    0.11
    æĶ»
    0.11
    attack
    0.10
    _scan
    0.10
    _attack
    0.10
    .scan
    0.10
    .Scan
    0.09
    管家
    0.09
     wÅĤ
    0.09
    .foundation
    0.09
    Activations Density 0.349%

    No Known Activations