© 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. 18207
    Prev
    Next
    INDEX
    Explanations

    say "voice"

    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
    è¡Ĺ
    -0.29
    è·¯
    -0.28
    itty
    -0.27
    bis
    -0.26
    ä½İ
    -0.26
    itti
    -0.26
    åĬ³
    -0.26
    abi
    -0.26
     leg
    -0.25
    èħ¿
    -0.25
    POSITIVE LOGITS
    ONO
    0.30
     spirit
    0.26
    fal
    0.26
    oger
    0.25
    cco
    0.25
    çĶ·ä¸»è§Ĵ
    0.25
    ãĤ¹ãĥŀ
    0.24
    mgr
    0.24
     fal
    0.24
     voice
    0.24
    Activations Density 0.556%

    No Known Activations