© 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. 14-TRANSCODER-HP
    7. 39672
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Negative Logits
     pitched
    -0.30
    yla
    -0.29
    ä¸Ģç»ı
    -0.28
     Lust
    -0.27
    Æ°á»Ŀ
    -0.26
    pitch
    -0.25
    Ty
    -0.25
    æIJħ
    -0.25
     personally
    -0.24
     pitch
    -0.24
    POSITIVE LOGITS
    ãĤĵãģ§ãģĻãģijãģ©
    0.27
     yếu
    0.27
    æµĨ
    0.26
    ä»Ģä¹Īåij¢
    0.26
    ç»ĵ
    0.26
     *@
    0.25
    onto
    0.25
    äºĽä»Ģä¹Ī
    0.24
    ÑģÑĤанавлива
    0.24
    inging
    0.24
    Activations Density 1.224%

    No Known Activations