© 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. 31-TRANSCODER-HP
    7. 19555
    Prev
    Next
    INDEX
    Explanations

    Her

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¥èµ·
    -0.32
     Coff
    -0.28
     desn
    -0.28
    elon
    -0.27
    -addons
    -0.27
    elden
    -0.26
     ATF
    -0.26
    istle
    -0.25
    aday
    -0.25
    owan
    -0.25
    POSITIVE LOGITS
     fibre
    0.30
    ÑĦÑĢ
    0.29
    ibre
    0.28
     content
    0.26
     BM
    0.26
    /show
    0.26
     che
    0.26
     cite
    0.25
    auce
    0.25
    çIJĨ
    0.25
    Activations Density 0.108%

    No Known Activations