© 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. 40511
    Prev
    Next
    INDEX
    Explanations

    Punctuation and code snippets

    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
    å¼¹
    -0.30
    ä»»
    -0.28
    á»®
    -0.27
    å½Ī
    -0.27
    ,application
    -0.27
    åĢį
    -0.26
    asket
    -0.25
    isti
    -0.25
    inet
    -0.25
    oit
    -0.25
    POSITIVE LOGITS
     refl
    0.28
    æŶéĹ´åĨħ
    0.27
    æ¶īåıĬåĪ°
    0.26
    ä¸Ģå¥Ĺ
    0.26
    æݾ
    0.26
    .ExecuteNonQuery
    0.25
     anth
    0.25
     sleeper
    0.25
    abouts
    0.24
    ä¸Ģç»ı
    0.24
    Activations Density 0.009%

    No Known Activations