© 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. 25-TRANSCODER-HP
    7. 108698
    Prev
    Next
    INDEX
    Explanations

    Fed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    辦çIJĨ
    -0.28
    ç»Ĭ
    -0.26
    oup
    -0.26
    Formats
    -0.25
    çī¯
    -0.25
    åĬŀçIJĨ
    -0.24
    èĥ¸æĢĢ
    -0.24
     Implicit
    -0.24
    cheng
    -0.24
    ä¸Ģäºĭ
    -0.24
    POSITIVE LOGITS
    iture
    0.32
    isory
    0.26
    ello
    0.26
    UNICATION
    0.25
    ERICA
    0.25
    紧紧
    0.25
    æĤ¬æĮĤ
    0.25
    rica
    0.25
    ucid
    0.25
    éĩıåĮĸ
    0.25
    Activations Density 0.040%

    No Known Activations