© 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. 54822
    Prev
    Next
    INDEX
    Explanations

    stability and instability

    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
    ordo
    -0.10
    åı£è¢ĭ
    -0.09
    IID
    -0.08
    çĬ¶åħĥ
    -0.08
    APPED
    -0.08
    cci
    -0.08
    çľ¼éĩĮ
    -0.08
    æİĢ
    -0.08
    RID
    -0.08
     Verg
    -0.08
    POSITIVE LOGITS
    稳å®ļçļĦ
    0.23
    稳å®ļæĢ§
    0.22
    稳å®ļ
    0.21
    ç©©å®ļ
    0.19
     stability
    0.18
     Stability
    0.16
    ä¸į稳å®ļ
    0.16
    ç¨³åĽº
    0.15
     stable
    0.14
    åı¯éĿłæĢ§
    0.14
    Activations Density 0.089%

    No Known Activations