© 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. 42571
    Prev
    Next
    INDEX
    Explanations

    this

    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
     law
    -0.26
    æ³ķ
    -0.26
    èī
    -0.26
    橹
    -0.26
    DidChange
    -0.26
    types
    -0.25
    å¦Ĥä½ķåİ»
    -0.25
    æ¹ĸåĮº
    -0.24
    çİĩ为
    -0.24
    law
    -0.24
    POSITIVE LOGITS
     show
    0.35
     SHOW
    0.33
     showed
    0.32
     shown
    0.32
    Show
    0.30
    SHOW
    0.30
    	show
    0.30
    ä¾
    0.29
    _show
    0.29
     Show
    0.29
    Activations Density 0.002%

    No Known Activations