© 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. 22-TRANSCODER-HP
    7. 98415
    Prev
    Next
    INDEX
    Explanations

    directed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     couch
    -0.27
     hạ
    -0.25
    atta
    -0.25
    æģº
    -0.24
    è´¬
    -0.24
    ä¸įåIJ«
    -0.24
     Subscription
    -0.24
     ε
    -0.24
    amentos
    -0.23
    ansk
    -0.23
    POSITIVE LOGITS
    OST
    0.30
     joint
    0.28
    èģĶåIJĪ
    0.26
    èģ¯åIJĪ
    0.26
    常åĬ¡åī¯
    0.26
     MOM
    0.26
    ilit
    0.25
    ä¸Ģè§Ĵ
    0.25
    lder
    0.25
    å¾ĹåĪ°äºĨ
    0.25
    Activations Density 0.036%

    No Known Activations