© 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. 108183
    Prev
    Next
    INDEX
    Explanations

    Unstructured text/code snippets

    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
    äºĶæĺŁ
    -0.30
    okies
    -0.29
    ublisher
    -0.27
    åıijåĬ¨
    -0.26
    çī©çIJĨåѦ
    -0.26
     timelines
    -0.25
    èĥĥåı£
    -0.25
    .cv
    -0.24
    åĪ¶åº¦æĶ¹éĿ©
    -0.24
    ues
    -0.24
    POSITIVE LOGITS
    asp
    0.27
    tz
    0.27
     Above
    0.26
    ãĤ«ãĥ©
    0.25
    tty
    0.25
    -II
    0.25
    以ä¸Ĭãģ®
    0.25
    顯
    0.24
     Frontier
    0.23
    аÑĨи
    0.23
    Activations Density 0.893%

    No Known Activations