© 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. 22-TRANSCODER-HP
    7. 87748
    Prev
    Next
    INDEX
    Explanations

    ways of doing things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prompt
    -0.27
     chắn
    -0.26
    (prompt
    -0.26
    ukkan
    -0.26
    æİ¥åıĹ
    -0.26
    ä¸Ģ件äºĭæĥħ
    -0.25
    pedia
    -0.24
    prompt
    -0.24
    ereum
    -0.24
    sylvania
    -0.24
    POSITIVE LOGITS
    第äºĮç§į
    0.27
    :
    0.27
    setType
    0.26
    éĢļ常æĺ¯
    0.25
    ä¸ĭ车
    0.25
    åıijå±ķéĺ¶æ®µ
    0.25
     defaultMessage
    0.25
     RouteServiceProvider
    0.24
    asi
    0.24
     *(*
    0.24
    Activations Density 0.025%

    No Known Activations