© 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. 40700
    Prev
    Next
    INDEX
    Explanations

    morality and judgment

    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
     Pf
    -0.27
     investig
    -0.27
    @stop
    -0.26
    ä¾¦å¯Ł
    -0.25
    ä¸įæĪIJ
    -0.25
    ngle
    -0.25
     reconnaissance
    -0.25
    èª¿æŁ¥
    -0.25
    etro
    -0.25
     Invest
    -0.25
    POSITIVE LOGITS
    makt
    0.33
    OU
    0.27
    ersh
    0.26
    让æĪij
    0.26
    tier
    0.26
    sie
    0.26
    linkplain
    0.25
     bump
    0.25
    让æĪij们
    0.25
     mixing
    0.25
    Activations Density 1.788%

    No Known Activations