© 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. 42980
    Prev
    Next
    INDEX
    Explanations

    What

    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
     My
    -0.36
     my
    -0.34
     that
    -0.33
     your
    -0.32
     ?
    -0.32
     Do
    -0.32
     Is
    -0.31
     That
    -0.30
     Not
    -0.30
    My
    -0.30
    POSITIVE LOGITS
    çī¹çĤ¹æĺ¯
    0.26
     specializes
    0.26
    aret
    0.26
    ’ll
    0.25
    ’re
    0.25
    éĥ½ä¼ļæľī
    0.25
     cruz
    0.24
    ìŀIJëĬĶ
    0.24
    AGING
    0.24
    rough
    0.24
    Activations Density 0.009%

    No Known Activations