© 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. 19-TRANSCODER-HP
    7. 8649
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĵįåºĶ
    -0.27
    yü
    -0.27
    å±Ģåī¯å±Ģéķ¿
    -0.27
    å±Ģå±Ģéķ¿
    -0.26
    	Description
    -0.25
    estate
    -0.25
    (IM
    -0.25
    asename
    -0.24
    å±Ģ
    -0.24
    åħ·ä½ĵ
    -0.24
    POSITIVE LOGITS
    iss
    0.31
    åĽº
    0.26
     optionally
    0.26
     membr
    0.26
    ä¸įåĪ©
    0.26
    å¾Ĺå¾Ī
    0.25
    HttpServletRequest
    0.25
    éĴĪ
    0.24
    çĺ¦
    0.24
    ä¾Ŀæ³ķ追究
    0.24
    Activations Density 0.002%

    No Known Activations