© 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. 14-TRANSCODER-HP
    7. 39918
    Prev
    Next
    INDEX
    Explanations

    yellow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çı¾åł´
    -0.27
    åĬłçĽŁ
    -0.26
     toxicity
    -0.26
    ottle
    -0.25
     Borough
    -0.25
    .blur
    -0.25
    çĦī
    -0.25
     uncomfortable
    -0.24
    odied
    -0.24
    éģŃåĪ°
    -0.24
    POSITIVE LOGITS
    æĮĤéĴ©
    0.28
    [url
    0.28
    ä½ı
    0.27
    éĵ¢
    0.27
    och
    0.26
     Nimbus
    0.26
     noqa
    0.26
    pack
    0.25
    èĢ³
    0.25
    ä¸Ńåħ³
    0.25
    Activations Density 0.182%

    No Known Activations