© 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. 41989
    Prev
    Next
    INDEX
    Explanations

    school and learning

    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
    å§Ķæīĺ
    -0.30
    å¸ĪèĮĥ
    -0.28
     professors
    -0.28
    éĢļ
    -0.26
     advoc
    -0.26
    aze
    -0.26
    istrar
    -0.25
    ÑģÑĤеÑĢ
    -0.25
    æģ£
    -0.25
     entrusted
    -0.25
    POSITIVE LOGITS
    note
    0.34
     note
    0.33
     scientific
    0.30
    ç»Ħ
    0.30
     organization
    0.28
     group
    0.28
    inet
    0.28
    å®ģ
    0.28
    ëĵł
    0.28
     notice
    0.26
    Activations Density 0.001%

    No Known Activations