© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56314
    Prev
    Next
    INDEX
    Explanations

    Negation of phrases

    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
    Negative Logits
    opro
    -0.29
    forth
    -0.27
    //{{
    -0.27
    .Help
    -0.27
    è¿ĻçĤ¹
    -0.26
    edia
    -0.26
    leck
    -0.26
    è¿Ļ个éĹ®é¢ĺ
    -0.26
    ViewState
    -0.25
    //}}
    -0.25
    POSITIVE LOGITS
    night
    0.26
    (optional
    0.25
     closes
    0.25
    ä½ĵåĨħ
    0.24
     PARTICULAR
    0.24
    (side
    0.23
    å¸ĺ
    0.23
    红éħĴ
    0.23
    æŶ
    0.23
    osition
    0.23
    Activations Density 0.021%

    No Known Activations