© 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. 130143
    Prev
    Next
    INDEX
    Explanations

    known

    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
    Witness
    -0.28
    æĢ»æĶ¶åħ¥
    -0.28
    å°ıæĻĤ
    -0.27
     Utf
    -0.26
    testdata
    -0.25
    GetObject
    -0.25
    åĤ·
    -0.24
    cf
    -0.23
    missions
    -0.23
    ookies
    -0.23
    POSITIVE LOGITS
    pare
    0.30
     historical
    0.29
    owitz
    0.27
     Bon
    0.27
    edly
    0.27
    äºĨä¸Ģç³»åĪĹ
    0.27
    ç»ıè¿ĩå¤ļå¹´
    0.27
    ABCDE
    0.26
    ä¸İæĹ¶ä¿±è¿Ľ
    0.26
    oro
    0.26
    Activations Density 0.036%

    No Known Activations