© 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. 33-TRANSCODER-HP
    7. 54355
    Prev
    Next
    INDEX
    Explanations

    Legal/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æģķ
    -0.32
     Spell
    -0.28
    gu
    -0.27
    BarButton
    -0.26
    assigned
    -0.26
    åķĨä¼ļ
    -0.25
    èIJ½åIJİ
    -0.25
    éļı
    -0.24
    Assigned
    -0.24
     assigned
    -0.24
    POSITIVE LOGITS
    éŀĺ
    0.33
    Knight
    0.25
     reflex
    0.24
    _AX
    0.24
    ä¸ĢåĽŀäºĭ
    0.24
     Cres
    0.24
    anan
    0.24
     pants
    0.24
    è°ĥæŁ¥
    0.24
    ksen
    0.24
    Activations Density 0.015%

    No Known Activations