© 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. 30-TRANSCODER-HP
    7. 95863
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isons
    -0.29
    phabet
    -0.29
    ä¾ĭå¤ĸ
    -0.28
    loys
    -0.27
    eway
    -0.27
    ely
    -0.26
    phrase
    -0.26
    abel
    -0.26
     DRV
    -0.25
    stell
    -0.25
    POSITIVE LOGITS
    å¼łæī¬
    0.26
    ENO
    0.26
    ænd
    0.25
    è¡ĮåĬ¨è®¡åĪĴ
    0.25
     owner
    0.24
    计åĪĴ
    0.24
     Owner
    0.24
    olie
    0.24
    _deck
    0.23
    满äºĨ
    0.23
    Activations Density 0.884%

    No Known Activations