© 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. 24-TRANSCODER-HP
    7. 150194
    Prev
    Next
    INDEX
    Explanations

    health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çIJı
    -0.26
    æŃ£å¸¸ä½¿çĶ¨
    -0.26
    ropriate
    -0.26
     setContent
    -0.26
    -flag
    -0.25
     setImage
    -0.24
    icip
    -0.24
    -describedby
    -0.24
    .setUser
    -0.24
    ahi
    -0.24
    POSITIVE LOGITS
    åľ°ä¸Ĭ
    0.28
    æ¯ı个人çļĦ
    0.26
     лÑİдей
    0.26
    驯
    0.26
     mins
    0.26
    人ãģ®
    0.26
    è§Ĥ
    0.25
     Menschen
    0.25
    人们çļĦ
    0.25
    人æ°Ķ
    0.25
    Activations Density 0.191%

    No Known Activations