© 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. 39954
    Prev
    Next
    INDEX
    Explanations

    commercial/legal contexts

    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
     Cities
    -0.28
    Wall
    -0.26
    wall
    -0.26
    举
    -0.25
    plants
    -0.25
    åĶ¯
    -0.25
     dokÅĤadnie
    -0.25
    à¹Ħฮ
    -0.25
    两款
    -0.25
    oi
    -0.24
    POSITIVE LOGITS
    èµĸ以
    0.37
     therefore
    0.33
     stop
    0.29
     knowledge
    0.28
     localization
    0.28
     preparation
    0.27
     statistics
    0.27
     unreal
    0.27
     infrastructure
    0.26
     authorization
    0.26
    Activations Density 53.557%

    No Known Activations