© 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. 22701
    Prev
    Next
    INDEX
    Explanations

    room or space

    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
    åĸľæ¬¢åIJĥ
    -0.10
    梦幻
    -0.09
    èģĬèģĬ
    -0.09
    åį§
    -0.09
    å¥ģ
    -0.09
    opsis
    -0.09
    éĴ»
    -0.09
    ä¸įæŃ»
    -0.09
    åĽ¢éķ¿
    -0.09
    çĥĤ
    -0.09
    POSITIVE LOGITS
    室åĨħ
    0.17
     room
    0.16
    æĪ¿éĹ´
    0.15
    æķĻ室
    0.15
    室
    0.15
    客åİħ
    0.15
    大åİħ
    0.15
    空éĹ´
    0.14
     rooms
    0.14
     space
    0.13
    Activations Density 0.113%

    No Known Activations