© 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. 8895
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ⽯
    -0.27
    ÙĦÙĪØŃ
    -0.27
     Installing
    -0.27
    ä¼ģä¸ļæıIJä¾Ľ
    -0.26
    strup
    -0.25
    esen
    -0.25
    steller
    -0.25
     olduÄŁunu
    -0.25
    Installing
    -0.24
     olmadıģını
    -0.24
    POSITIVE LOGITS
     when
    0.44
    when
    0.38
    çļĦæŶåĢĻ
    0.36
    æŶåĢĻ
    0.36
     cuando
    0.33
     quando
    0.33
     когда
    0.32
    When
    0.31
     khi
    0.31
     part
    0.29
    Activations Density 0.009%

    No Known Activations