© 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. 54015
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ancement
    -0.31
    ?key
    -0.29
    drive
    -0.29
    resolution
    -0.28
    dle
    -0.28
    èµĿ
    -0.27
    ancies
    -0.27
     inc
    -0.26
    ency
    -0.26
    PageIndex
    -0.26
    POSITIVE LOGITS
     Casual
    0.33
    ÅĽci
    0.28
    åıĮ
    0.28
    fr
    0.27
     flu
    0.26
     Sp
    0.26
    F
    0.26
    TF
    0.26
    sp
    0.26
    å¼¹
    0.26
    Activations Density 0.018%

    No Known Activations