© 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. 27-TRANSCODER-HP
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stakes
    -0.28
    chk
    -0.26
    staff
    -0.26
    /pkg
    -0.26
    èªł
    -0.25
     sincer
    -0.24
    /lic
    -0.24
    stab
    -0.24
    /rem
    -0.24
    è¡Įãģį
    -0.24
    POSITIVE LOGITS
    .observe
    0.28
    ivated
    0.28
    åĨ²
    0.27
    Hp
    0.25
    ivate
    0.25
    float
    0.25
     float
    0.25
    æįķ
    0.25
     hr
    0.24
    cpy
    0.24
    Activations Density 0.024%

    No Known Activations