© 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. 53165
    Prev
    Next
    INDEX
    Explanations

    without

    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
    hil
    -0.28
    ISE
    -0.26
     harsh
    -0.26
    ASTER
    -0.26
     clever
    -0.24
    æĶ¾è¿ĩ
    -0.24
    åŁºæľ¬ä¸Ĭ
    -0.24
    çľĭ好
    -0.24
    hões
    -0.23
     reconstruct
    -0.23
    POSITIVE LOGITS
    é¢IJ
    0.28
    Own
    0.28
    é¢ľ
    0.25
    (define
    0.25
    енÑĭ
    0.24
    èĩªå®¶
    0.24
     entering
    0.24
    esson
    0.23
    prior
    0.23
     earning
    0.23
    Activations Density 0.019%

    No Known Activations