© 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. 35-TRANSCODER-HP
    7. 40008
    Prev
    Next
    INDEX
    Explanations

    Code and licensing snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     needing
    -0.29
     making
    -0.28
    为ä¹ĭ
    -0.26
     overse
    -0.26
     vulgar
    -0.26
     violent
    -0.25
     committing
    -0.24
     UsersController
    -0.24
     freelance
    -0.24
     FAR
    -0.24
    POSITIVE LOGITS
    amax
    0.30
    LÄ°
    0.27
     dat
    0.27
    оÑģоб
    0.26
     clearly
    0.24
     Mojo
    0.24
    æŃ£å¸¸
    0.24
    cuts
    0.24
    0.24
     normal
    0.24
    Activations Density 0.088%

    No Known Activations