© 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. 95539
    Prev
    Next
    INDEX
    Explanations

    Scientific research papers

    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
     bob
    -0.31
     elast
    -0.30
    å¼¹
    -0.27
     elastic
    -0.26
    ä»ĭè´¨
    -0.26
    throw
    -0.26
    elp
    -0.25
     Cout
    -0.25
     theta
    -0.24
    egl
    -0.24
    POSITIVE LOGITS
    fre
    0.28
    è·ijæŃ¥
    0.27
     matter
    0.26
    matter
    0.26
    çĥŃçĪ±
    0.26
     upstream
    0.26
    _optimizer
    0.26
    	pw
    0.26
     lul
    0.24
     Skinner
    0.24
    Activations Density 0.106%

    No Known Activations