© 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. 18-TRANSCODER-HP
    7. 89492
    Prev
    Next
    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ°æ¯¯
    -0.26
    gatsby
    -0.26
    ä»Ĺ
    -0.26
    ãģ¨ãģĵãĤį
    -0.25
     combinations
    -0.25
    erequisites
    -0.24
    uset
    -0.24
    常è¯Ĩ
    -0.24
    ÄĻp
    -0.24
    apeutics
    -0.24
    POSITIVE LOGITS
    ami
    0.28
    æĢ»æľī
    0.27
    AMI
    0.27
    çļĦçĭ¬çī¹
    0.26
    (Frame
    0.26
    ammed
    0.25
    him
    0.24
    .atomic
    0.24
    ä¹ŁæĹłæ³ķ
    0.24
    ä¸įå°½
    0.24
    Activations Density 27.944%

    No Known Activations