© 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. 53965
    Prev
    Next
    INDEX
    Explanations

    rel

    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
     marking
    -0.29
     physically
    -0.28
     scheme
    -0.26
    (er
    -0.25
    éĹ®çŃĶ
    -0.24
    oth
    -0.24
    bbe
    -0.24
     practice
    -0.23
     program
    -0.23
     mit
    -0.23
    POSITIVE LOGITS
    ités
    0.26
    iances
    0.26
    èIJ½åľ¨
    0.25
    ิà¸ķ
    0.25
    ective
    0.25
    å´ĸ
    0.24
    irect
    0.24
    è´§
    0.23
    èIJ½åľ°
    0.23
     reprodu
    0.23
    Activations Density 0.005%

    No Known Activations