© 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. 53774
    Prev
    Next
    INDEX
    Explanations

    patents and legal claims

    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
    éĥ¨åī¯
    -0.29
     CAPITAL
    -0.29
    Pk
    -0.28
    passes
    -0.28
     JB
    -0.28
    motion
    -0.27
    ackers
    -0.27
     zro
    -0.26
    æĹ¶ä»£çļĦ
    -0.26
    æ»´
    -0.26
    POSITIVE LOGITS
     legal
    0.32
     ir
    0.31
    ora
    0.29
     bele
    0.28
    legal
    0.28
     cont
    0.26
     juris
    0.26
    ç»Ŀ
    0.26
     anthrop
    0.26
    ov
    0.26
    Activations Density 0.121%

    No Known Activations