© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36068
    Prev
    Next
    INDEX
    Explanations

    view / views / overlooking / obstructed

    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
    ä¸įæĿ¥
    -0.09
    heet
    -0.08
    ä¸įä¿¡
    -0.08
    èĥŃ
    -0.08
    åı¸
    -0.08
    æĭ³å¤´
    -0.08
    æ¶ī足
    -0.08
    .xy
    -0.08
     Bender
    -0.08
    ct
    -0.08
    POSITIVE LOGITS
    è§Ĩéĩİ
    0.19
     views
    0.16
    çľº
    0.15
     view
    0.15
     Blick
    0.14
    è§Ĩè§Ĵ
    0.14
    èĥ½çľĭåĪ°
    0.14
    æľĽåİ»
    0.13
    è§Ĩ线
    0.13
     overlooking
    0.12
    Activations Density 0.067%

    No Known Activations