© 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. 14-TRANSCODER-HP
    7. 41001
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĮ
    -0.28
    第äºĮç§į
    -0.28
    è¿Ļ两ç§į
    -0.27
    bam
    -0.26
    atur
    -0.26
    两ç§į
    -0.25
    沸èħ¾
    -0.24
    aneous
    -0.24
    urst
    -0.24
    bum
    -0.24
    POSITIVE LOGITS
    ä¸į该
    0.29
    å§ĵ
    0.28
    [Unit
    0.28
    å·©
    0.27
    _ser
    0.25
    æIJĵ
    0.25
    åºĶæĢ¥
    0.25
    éĥ½çŁ¥éģĵ
    0.25
    ä¸įæ¸ħæ¥ļ
    0.24
     Ser
    0.24
    Activations Density 1.034%

    No Known Activations