© 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. 57406
    Prev
    Next
    INDEX
    Explanations

    room/bedroom locations

    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
     convoy
    -0.10
    ILD
    -0.09
    åĬŃ
    -0.09
    aaaaaaaa
    -0.09
    ead
    -0.09
    vor
    -0.09
    家乡
    -0.08
    车éĺŁ
    -0.08
    æµ·ä¸Ĭ
    -0.08
    饥
    -0.08
    POSITIVE LOGITS
    åį§å®¤
    0.15
    rooms
    0.14
    æĪ¿éĹ´
    0.14
     rooms
    0.13
    .Room
    0.13
     bedrooms
    0.12
     room
    0.12
    (Room
    0.12
    -room
    0.12
    ROOM
    0.12
    Activations Density 0.070%

    No Known Activations