© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52005
    Prev
    Next
    INDEX
    Explanations

    recording information

    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
    ipes
    -0.11
    itia
    -0.10
    пÑĢоÑģ
    -0.10
    .sent
    -0.09
    _METADATA
    -0.09
    ResponseType
    -0.09
    CAA
    -0.09
    éĻIJ
    -0.09
    æī¶
    -0.09
    hog
    -0.09
    POSITIVE LOGITS
    è®°å½ķ
    0.16
    è®°
    0.14
    纪å½ķ
    0.13
    è®°è½½
    0.13
    è¨ĺéĮĦ
    0.12
     record
    0.12
    å½ķ
    0.11
    åĨĻä¸ĭ
    0.11
     recording
    0.11
    ç¬Ķè®°
    0.11
    Activations Density 0.136%

    No Known Activations