© 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. 88516
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment/opinions

    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
     fails
    -0.28
    继ç»Ńä¿ĿæĮģ
    -0.27
    åĻ¤
    -0.26
    (Parcel
    -0.26
    ä¹ŁæĹłæ³ķ
    -0.26
    	fail
    -0.26
    fail
    -0.25
     fail
    -0.25
    æ¶īå«Į
    -0.25
    å°±ä¸įèĥ½
    -0.25
    POSITIVE LOGITS
     relief
    0.32
    Enjoy
    0.31
    æĪIJåĬŁ
    0.29
    è¾īçħĮ
    0.28
     comfortable
    0.28
     miracle
    0.28
    享åıĹ
    0.28
     profitable
    0.27
    éĿł
    0.27
     happy
    0.26
    Activations Density 0.004%

    No Known Activations