© 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. 8061
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     favor
    -0.27
     identity
    -0.26
    åħ¬å¸ĥäºĨ
    -0.25
    <$
    -0.25
    åŃĹ
    -0.25
    odiac
    -0.24
    ste
    -0.24
    nom
    -0.24
    ÑĤив
    -0.24
    å®ıè§Ĥç»ıæµİ
    -0.24
    POSITIVE LOGITS
    oad
    0.28
    embre
    0.27
    brtc
    0.27
    æĭ¦æĪª
    0.26
    æŃ¼
    0.25
    rames
    0.25
     cerr
    0.24
    æ®ļ
    0.24
    craper
    0.24
    ading
    0.24
    Activations Density 0.009%

    No Known Activations