© 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. 109300
    Prev
    Next
    INDEX
    Explanations

    on

    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
    odic
    -0.27
     Forbes
    -0.25
    è£ĺ
    -0.24
    é¹ĺ
    -0.24
    erry
    -0.24
    _REDIRECT
    -0.24
    dana
    -0.23
    uada
    -0.23
     inverted
    -0.23
    ankind
    -0.23
    POSITIVE LOGITS
    å±ŀ
    0.31
    cab
    0.28
    åĻªéŁ³
    0.27
    强度
    0.27
    款å¼ı
    0.26
     disturbance
    0.25
    åĴ©
    0.25
    åįļå¼Ī
    0.25
    å±ı
    0.25
    *T
    0.25
    Activations Density 0.901%

    No Known Activations