© 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. 9076
    Prev
    Next
    INDEX
    Explanations

    which, that

    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
    conde
    -0.31
    åĨĻçĿĢ
    -0.29
    autoload
    -0.28
     interfering
    -0.26
    ä¸Ģä½ĵåĮĸ
    -0.26
     choked
    -0.26
     overloaded
    -0.26
    æݥ轨
    -0.25
     refusing
    -0.25
     impacting
    -0.25
    POSITIVE LOGITS
    åĪ©çĶ¨
    0.31
     uses
    0.30
    ä¾ĿéĿł
    0.29
    æĪijèĥ½
    0.29
     sá»Ń
    0.28
     RedirectTo
    0.28
    温室
    0.27
    amer
    0.27
    	Use
    0.27
    æĬķæĶ¾
    0.26
    Activations Density 0.009%

    No Known Activations