© 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. 25-TRANSCODER-HP
    7. 107174
    Prev
    Next
    INDEX
    Explanations

    relaxation and soothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Cb
    -0.26
     tightly
    -0.26
    çķĮ
    -0.26
    ec
    -0.26
     guard
    -0.25
    kur
    -0.25
    ida
    -0.25
    iative
    -0.24
    /AP
    -0.24
    tight
    -0.24
    POSITIVE LOGITS
    ignet
    0.32
    让æ¶Īè´¹èĢħ
    0.30
    oyer
    0.26
    è¡Ģ液循çݯ
    0.26
    joy
    0.25
     transitions
    0.25
     travelers
    0.24
     sufferers
    0.24
    å¤ļ人
    0.24
    lear
    0.24
    Activations Density 0.998%

    No Known Activations