© 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. 27-TRANSCODER-HP
    7. 8762
    Prev
    Next
    INDEX
    Explanations

    relative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭįæĭį
    -0.28
    åIJĮç±»
    -0.28
    ä¸Ģåı°
    -0.26
    ref
    -0.25
    ather
    -0.24
    stown
    -0.24
    ese
    -0.24
    èĤ¢
    -0.23
    ä¸Ģåľº
    -0.23
    bec
    -0.23
    POSITIVE LOGITS
    æķĪçİĩ
    0.42
     efficiency
    0.36
     effectiveness
    0.34
    æķĪèĥ½
    0.33
     potency
    0.33
    æķĪæŀľ
    0.33
     size
    0.31
     responsiveness
    0.30
     efficacy
    0.29
    etween
    0.28
    Activations Density 0.014%

    No Known Activations