© 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. 30-TRANSCODER-HP
    7. 95871
    Prev
    Next
    INDEX
    Explanations

    theory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assum
    -0.27
    Freedom
    -0.26
     *&
    -0.26
    cheme
    -0.26
     Helm
    -0.25
    ç»ĦæĪIJ
    -0.25
    Attempts
    -0.25
    åĵĴ
    -0.23
     Attempts
    -0.23
     Routes
    -0.23
    POSITIVE LOGITS
     theory
    0.43
    çIJĨ论
    0.42
     Theory
    0.41
    Theory
    0.35
    theory
    0.33
     theorists
    0.31
    åIJ¹
    0.31
    çIJĨè«ĸ
    0.30
     epoch
    0.28
     Astronomy
    0.28
    Activations Density 0.103%

    No Known Activations