© 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. 57507
    Prev
    Next
    INDEX
    Explanations

    era

    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
    tat
    -0.24
    yz
    -0.23
    //{{
    -0.23
    æĹĹå¸ľ
    -0.23
    loat
    -0.23
    iens
    -0.23
    ç§ĭåŃ£
    -0.23
    nant
    -0.23
     STORY
    -0.23
     اÙĦشر
    -0.23
    POSITIVE LOGITS
     when
    0.29
     когда
    0.26
    when
    0.26
     When
    0.25
     cuando
    0.24
     commuters
    0.24
    When
    0.24
    باس
    0.24
     CID
    0.24
    [code
    0.24
    Activations Density 0.044%

    No Known Activations