© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 26776
    Prev
    Next
    INDEX
    Explanations

    pitch or pitchfork

    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
    æĮĩ示
    -0.10
    ç¼ķ
    -0.09
    表æĥħ
    -0.08
    èĮĦ
    -0.08
    cient
    -0.08
    .stamp
    -0.08
    çĥĺå¹²
    -0.08
     Musk
    -0.08
    ä¾Ľç»Ļ
    -0.08
    ,ev
    -0.08
    POSITIVE LOGITS
    pitch
    0.14
    Pitch
    0.12
     pitch
    0.11
     pitched
    0.10
     Pitch
    0.10
     pitches
    0.10
     pitching
    0.10
    .pitch
    0.09
    _pitch
    0.09
    æłĩçļĦ
    0.09
    Activations Density 0.005%

    No Known Activations