© 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. 9-TRANSCODER-HP
    7. 29586
    Prev
    Next
    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Technique
    -0.28
    vero
    -0.27
    äºĨåIJ§
    -0.27
     ['#
    -0.27
    olist
    -0.25
    æĭ³
    -0.25
    çŁ¥è¯ĨçĤ¹
    -0.25
    Vari
    -0.25
     correctly
    -0.25
     Vari
    -0.24
    POSITIVE LOGITS
    ical
    0.28
    иÑĩеÑģкаÑı
    0.27
    ä»ĺåĩº
    0.26
    çĽijçIJĨ
    0.25
    ricular
    0.25
    ioneer
    0.25
    éģ¥
    0.25
    .Handled
    0.24
    ¾ç¤º
    0.24
    awai
    0.24
    Activations Density 0.726%

    No Known Activations