© 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. 35-TRANSCODER-HP
    7. 38985
    Prev
    Next
    INDEX
    Explanations

    COVID-19

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stal
    -0.28
    çīį
    -0.26
    roup
    -0.26
    è§ĴéĢIJ
    -0.25
     la
    -0.25
     d
    -0.25
    箸
    -0.25
     allure
    -0.25
     annum
    -0.24
     ust
    -0.24
    POSITIVE LOGITS
    iny
    0.34
    wi
    0.33
    inc
    0.32
    ematic
    0.32
    inv
    0.30
    ae
    0.29
    Vi
    0.29
    VIC
    0.29
    ema
    0.28
    -IN
    0.28
    Activations Density 51.403%

    No Known Activations