© 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. 43165
    Prev
    Next
    INDEX
    Explanations

    return

    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
     backs
    -0.47
     Back
    -0.42
    Back
    -0.42
     back
    -0.40
    backs
    -0.38
    èĥĮ
    -0.38
    -back
    -0.37
    back
    -0.36
    	back
    -0.36
    èĥĮä¸Ĭ
    -0.36
    POSITIVE LOGITS
     home
    0.47
     to
    0.34
     Home
    0.33
    home
    0.30
    cre
    0.30
     rather
    0.29
    .home
    0.28
     should
    0.28
     homes
    0.28
    Home
    0.28
    Activations Density 0.009%

    No Known Activations