© 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. 20-TRANSCODER-HP
    7. 130005
    Prev
    Next
    INDEX
    Explanations

    beginning of a text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramer
    -0.28
    ems
    -0.27
    éĤ
    -0.26
     Meet
    -0.26
    æ¦Ĥ
    -0.26
     herr
    -0.25
    æĸ°çīĪ
    -0.24
     Kick
    -0.24
    éĢļçĶ¨
    -0.24
    rypted
    -0.23
    POSITIVE LOGITS
    ä¸ĸçķĮ第ä¸Ģ
    0.28
    对åħ¶è¿Ľè¡Į
    0.28
    两边
    0.28
    è¢ĭ
    0.27
    transpose
    0.27
    ány
    0.26
    uron
    0.26
    è¥Ħ
    0.25
    .SizeF
    0.25
    ordo
    0.24
    Activations Density 27.311%

    No Known Activations