© 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. 30-TRANSCODER-HP
    7. 95940
    Prev
    Next
    INDEX
    Explanations

    such

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ĵéĩı
    -0.29
    .SIG
    -0.27
    manship
    -0.27
     paced
    -0.26
    é¦
    -0.26
    /interface
    -0.26
    Land
    -0.26
    sig
    -0.26
    SIG
    -0.26
     LAND
    -0.25
    POSITIVE LOGITS
     cr
    0.29
    ayar
    0.27
     Gale
    0.26
    .TRAN
    0.26
    big
    0.26
    ernals
    0.25
    æµ·æ¹¾
    0.25
    íĤ·
    0.24
    _big
    0.24
    indic
    0.24
    Activations Density 1.063%

    No Known Activations