© 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. 53739
    Prev
    Next
    INDEX
    Explanations

    software

    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
    arty
    -0.30
    ataire
    -0.27
    áĢĦ
    -0.26
     ofType
    -0.26
    aken
    -0.25
     Sp
    -0.25
    æ°¨
    -0.25
    ced
    -0.24
     trusted
    -0.24
    vac
    -0.24
    POSITIVE LOGITS
    èı²
    0.32
    InputModule
    0.28
    ä¸įè¿ĩ
    0.28
    éĩįå¡ij
    0.28
    说æĺ¯
    0.27
    OUSE
    0.27
    ä¸ĢæĹ¥
    0.27
     Bhar
    0.27
    ÑĦ
    0.26
    Ordered
    0.26
    Activations Density 0.050%

    No Known Activations