© 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. 20-TRANSCODER-HP
    7. 130463
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     improperly
    -0.48
     errone
    -0.44
     wrongly
    -0.43
     poorly
    -0.41
     mistakenly
    -0.40
     incorrectly
    -0.40
     inade
    -0.37
     improper
    -0.37
     inconsist
    -0.35
     illegally
    -0.35
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.35
    å¿ħè¦ģ
    0.30
    çķĻ
    0.29
    åıªéľĢè¦ģ
    0.28
    ardown
    0.28
     uniqu
    0.27
     disap
    0.26
     needed
    0.26
    kos
    0.26
    .jav
    0.26
    Activations Density 82.381%

    No Known Activations