© 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. 38718
    Prev
    Next
    INDEX
    Explanations

    want to express desire or need

    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
     vib
    -0.11
    locker
    -0.10
    phin
    -0.09
    íĴĢ
    -0.09
    bah
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    éĽħ
    -0.08
    åİ¥
    -0.08
    presso
    -0.08
    Bindable
    -0.08
    POSITIVE LOGITS
     needed
    0.13
    ä¹ŁéľĢè¦ģ
    0.12
    éľĢè¦ģ
    0.12
     Needed
    0.12
     необÑħодимо
    0.11
    ä½łéľĢè¦ģ
    0.11
    éľĢè¦ģçĶ¨
    0.11
    å¿ħè¦ģãģĮãģĤãĤĬãģ¾ãģĻ
    0.11
     нÑĥжнÑĭ
    0.11
     needs
    0.11
    Activations Density 0.200%

    No Known Activations