© 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. 35-TRANSCODER-HP
    7. 39672
    Prev
    Next
    INDEX
    Explanations

    Medical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢĶ
    -0.32
     I
    -0.30
    DEX
    -0.27
     implement
    -0.25
     implementations
    -0.25
    å®ŀçİ°
    -0.25
    dialog
    -0.25
    éĢĶå¾Ħ
    -0.25
    è¡Į
    -0.25
     scout
    -0.24
    POSITIVE LOGITS
     Dome
    0.30
    å²Ĥ
    0.30
    å¦Ĥä½ķåİ»
    0.28
     dome
    0.28
     weren
    0.26
    带
    0.25
    ViewItem
    0.25
     nucleus
    0.25
    idency
    0.24
    紧紧
    0.24
    Activations Density 0.436%

    No Known Activations