© 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. 42036
    Prev
    Next
    INDEX
    Explanations

    picture

    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
    ijľ
    -0.29
    Specifier
    -0.25
    ired
    -0.24
    abama
    -0.24
    hare
    -0.24
    IBLE
    -0.23
    paced
    -0.23
    éĶĢ
    -0.23
    umen
    -0.23
     hooked
    -0.22
    POSITIVE LOGITS
     picture
    1.79
    picture
    1.45
     Picture
    1.42
    Picture
    1.28
    -picture
    1.27
     pictures
    1.21
    _picture
    1.14
    .picture
    1.08
     pic
    1.03
     Pictures
    0.91
    Activations Density 0.002%

    No Known Activations