© 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. 8322
    Prev
    Next
    INDEX
    Explanations

    internet and research

    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
    åįģäºĮäºĶ
    -0.39
    æī¹å¤į
    -0.34
    æł¸åĩĨ
    -0.33
    æī¹
    -0.32
    åĽ½å®¶éĩįçĤ¹
    -0.31
    åįģåĽĽäºĶ
    -0.31
    æī¹åĩĨ
    -0.30
    åįģä¸īäºĶ
    -0.30
    çįŃ
    -0.28
    è´¢æĶ¿éĥ¨
    -0.28
    POSITIVE LOGITS
     mirror
    0.29
    éĻ¶çĵ·
    0.29
    éķľ
    0.28
     SceneManager
    0.27
    éı¡
    0.26
     Mirror
    0.25
     Position
    0.25
    é½ij
    0.25
    åĪĽéĢł
    0.24
     alle
    0.24
    Activations Density 0.004%

    No Known Activations