© 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. 54156
    Prev
    Next
    INDEX
    Explanations

    code/website context

    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
    ele
    -0.28
     sixth
    -0.27
    第åħŃ
    -0.27
     horns
    -0.25
    Configs
    -0.25
    第ä¸ī个
    -0.24
     setSearch
    -0.24
    æ¼ī
    -0.24
    æ·±å±Ĥ
    -0.23
     IX
    -0.23
    POSITIVE LOGITS
    ãĤ¹ãĥŀ
    0.28
    :+
    0.26
     –↵↵
    0.24
    (Bitmap
    0.24
    stm
    0.24
    ãģ¨ãģĦãģ£ãģ¦
    0.24
    ãģ¨ãĤĤ
    0.24
    /reference
    0.24
    LOT
    0.23
    olley
    0.23
    Activations Density 0.018%

    No Known Activations