© 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. 32364
    Prev
    Next
    INDEX
    Explanations

    Sony and Sonic references

    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
    OnChange
    -0.09
    è¢į
    -0.09
    icont
    -0.08
    sWith
    -0.08
    jen
    -0.08
    enance
    -0.08
    iphy
    -0.08
    ish
    -0.08
    бÑĢоÑģ
    -0.08
    Ñķ
    -0.08
    POSITIVE LOGITS
    èĩ´åij½
    0.10
    ç«ĭãģ¦
    0.10
    éĻįèIJ½
    0.09
    ä¸Ģéĥ¨
    0.09
    æĮ£
    0.09
    ARED
    0.09
    åĽŀé¦ĸ
    0.08
    èĥ½å¾ĹåĪ°
    0.08
    åıªè¦ģæľī
    0.08
    FER
    0.08
    Activations Density 0.016%

    No Known Activations