© 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. 54113
    Prev
    Next
    INDEX
    Explanations

    Mathematical simplification/solving

    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
    riage
    -0.27
     descriptors
    -0.26
     resetting
    -0.26
    riages
    -0.25
    çīĮåŃIJ
    -0.25
    éĹ©
    -0.25
    vat
    -0.25
     reset
    -0.24
    naments
    -0.24
    -reset
    -0.24
    POSITIVE LOGITS
     gives
    0.36
     risult
    0.31
     out
    0.31
     results
    0.29
     getResult
    0.29
    :↵↵
    0.28
     give
    0.28
     success
    0.28
    ,↵↵
    0.28
    ç»ĵæŀľ
    0.28
    Activations Density 0.015%

    No Known Activations