© 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. 63453
    Prev
    Next
    INDEX
    Explanations

    9

    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
    /write
    -0.26
    деÑģÑıÑĤ
    -0.25
    uble
    -0.23
     psychotic
    -0.22
    ptime
    -0.22
    EEE
    -0.22
     rinse
    -0.21
     conduct
    -0.21
    repid
    -0.21
     Soda
    -0.21
    POSITIVE LOGITS
    æĢ§çĸ¾çĹħ
    0.25
    HEN
    0.24
    (exports
    0.24
    ä¸ĢæŶ
    0.23
    frag
    0.23
    stit
    0.23
    èĵ¬
    0.22
    ience
    0.22
    è¦ģ
    0.22
    èIJ½å®ŀ
    0.21
    Activations Density 52.514%

    No Known Activations