© 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. 64080
    Prev
    Next
    INDEX
    Explanations

    Access and ownership

    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
    enburg
    -0.27
    sites
    -0.26
    æĤ»
    -0.26
    ä¸Ģæŀ¶
    -0.26
    åī¯éĻ¢éķ¿
    -0.25
    صار
    -0.25
    emble
    -0.25
     ÑĨен
    -0.25
    site
    -0.24
    ç¥ŀéĢļ
    -0.24
    POSITIVE LOGITS
    åºĬä¸Ĭ
    0.27
    oud
    0.25
    á»į
    0.25
    ders
    0.25
    avings
    0.25
    åĪĩ
    0.25
    myModal
    0.25
    hib
    0.24
    opleft
    0.24
    æŀľ
    0.24
    Activations Density 16.287%

    No Known Activations