© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52763
    Prev
    Next
    INDEX
    Explanations

    code related files

    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
    Negative Logits
    اغ
    -0.26
    oba
    -0.25
    SKTOP
    -0.25
    à¹Ħà¸ĭ
    -0.25
    æ©¡èĥ¶
    -0.25
     labour
    -0.25
    oa
    -0.25
     labor
    -0.25
     Blacks
    -0.24
    Labor
    -0.24
    POSITIVE LOGITS
    /Instruction
    0.27
     ç±
    0.27
    ide
    0.27
    æIJ¬å®¶
    0.26
    çĨ¨
    0.25
    渤
    0.24
    itures
    0.24
    licants
    0.24
     trim
    0.23
    ieee
    0.23
    Activations Density 0.016%

    No Known Activations