© 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. 95506
    Prev
    Next
    INDEX
    Explanations

    fruit

    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
    atak
    -0.28
    ulum
    -0.28
    à¹Ģà¸Ĺ
    -0.27
    asha
    -0.26
    INET
    -0.26
    è§Ħæł¼
    -0.25
    amped
    -0.25
    éĢ»è¾ij
    -0.24
     eauto
    -0.24
     ((__
    -0.24
    POSITIVE LOGITS
     fruit
    1.05
    fruit
    0.95
     Fruit
    0.92
     fruits
    0.85
     productive
    0.84
    æŀľ
    0.82
    æŀľå®ŀ
    0.74
     productivity
    0.73
     fruitful
    0.67
    productive
    0.66
    Activations Density 0.963%

    No Known Activations