© 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. 9-TRANSCODER-HP
    7. 29792
    Prev
    Next
    INDEX
    Explanations

    edge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     backstage
    -0.27
     BJP
    -0.26
    å«ģ
    -0.26
    BuilderInterface
    -0.25
    ettel
    -0.25
    è®©ä½ł
    -0.25
    SCALE
    -0.25
    =edge
    -0.25
     crow
    -0.24
    à¹Į
    -0.24
    POSITIVE LOGITS
    ivic
    0.27
    èĬĤå¥ı
    0.26
    (common
    0.26
     rhythm
    0.26
    ivor
    0.26
    æĭ³
    0.26
    åijĹ
    0.25
     rhyth
    0.25
     rhythms
    0.24
    ḿ
    0.24
    Activations Density 0.638%

    No Known Activations