© 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. 54313
    Prev
    Next
    INDEX
    Explanations

    metals and minerals

    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
    åŁİå¸Ĥ群
    -0.27
    _fg
    -0.26
    _Framework
    -0.25
    outing
    -0.25
     du
    -0.25
    /graphql
    -0.25
    -framework
    -0.24
     Croat
    -0.24
    ä¸įçĶ±
    -0.24
    Them
    -0.24
    POSITIVE LOGITS
    OR
    0.35
    ora
    0.30
    èĭ¥æľī
    0.28
    orse
    0.28
    ori
    0.28
    æŶè£ħ
    0.28
    ail
    0.28
    oria
    0.27
    ort
    0.27
    à¸Ńม
    0.27
    Activations Density 0.007%

    No Known Activations