© 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. 95553
    Prev
    Next
    INDEX
    Explanations

    from

    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
     sides
    -0.29
     side
    -0.28
    chè
    -0.28
     Side
    -0.26
    Side
    -0.26
    _side
    -0.25
    ÑģÑĤв
    -0.25
    åģ´
    -0.25
     confl
    -0.24
    LocalizedString
    -0.24
    POSITIVE LOGITS
     above
    0.32
    èĩªçĦ¶èĢĮ
    0.31
    以ä¸Ĭ
    0.28
    审
    0.28
    veled
    0.28
    以ä¸ĬçļĦ
    0.27
     below
    0.27
    bij
    0.27
    åħ¶ä¸Ńä¸Ģ个
    0.26
    åľ¨ä¸Ģ个
    0.25
    Activations Density 0.102%

    No Known Activations