© 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. 53872
    Prev
    Next
    INDEX
    Explanations

    special

    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
     cons
    -0.31
    éd
    -0.29
     ed
    -0.29
     rep
    -0.28
    itus
    -0.27
     tr
    -0.27
    istic
    -0.27
    ÑĢг
    -0.27
    itol
    -0.27
    sx
    -0.26
    POSITIVE LOGITS
    工夫
    0.28
    á»ĩn
    0.27
    eph
    0.26
    æ°¸è¿ľ
    0.25
    anonymous
    0.25
    ãģļ
    0.25
    unset
    0.24
     Quotes
    0.24
    çļĦ身份
    0.24
    (identity
    0.23
    Activations Density 0.016%

    No Known Activations