© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    绣
    -0.27
    å°±èĥ½
    -0.26
     neither
    -0.26
    Behaviour
    -0.25
     next
    -0.24
    ово
    -0.24
    overe
    -0.24
     mük
    -0.24
    ä¸įåĪ°
    -0.24
    blade
    -0.24
    POSITIVE LOGITS
     pur
    0.28
    powered
    0.28
     scenarios
    0.27
    BOR
    0.26
    PUR
    0.26
     maneuvers
    0.26
    anning
    0.26
     Scenario
    0.25
     Pur
    0.25
    typeof
    0.25
    Activations Density 0.027%

    No Known Activations