© 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. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42390
    Prev
    Next
    INDEX
    Explanations

    answer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astered
    -0.27
    sbin
    -0.26
    edb
    -0.26
    ldb
    -0.25
    è®°
    -0.25
    CLUS
    -0.24
    åºŁå¼ĥ
    -0.24
    ragon
    -0.24
     supplemental
    -0.24
    #End
    -0.24
    POSITIVE LOGITS
     to
    0.62
    	to
    0.38
    to
    0.36
    ìĿĦ
    0.30
    sto
    0.29
    ãĤĴ
    0.28
    ì§Ģ를
    0.27
     Ø¥ÙĦÙī
    0.27
    ,to
    0.26
    erto
    0.26
    Activations Density 0.012%

    No Known Activations