© 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. 112266
    Prev
    Next
    INDEX
    Explanations

    various news excerpts

    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
    cob
    -0.32
    çľĭä¸įåĪ°
    -0.27
    ANNOT
    -0.26
    ç»ıéĶĢ
    -0.25
    车åºĵ
    -0.24
    çľĭä¸įè§ģ
    -0.24
    æī¾ä¸įåĪ°
    -0.24
     modulus
    -0.24
    ç½ij讯
    -0.24
    numeric
    -0.23
    POSITIVE LOGITS
    éªļ
    0.29
    é¢Ĥ
    0.27
     alike
    0.27
    ä¸Ģæ³¢
    0.25
     caution
    0.24
    ault
    0.24
    åĦ¿
    0.24
    æĬĵç´§
    0.24
     ÐĺÑģ
    0.24
    atum
    0.23
    Activations Density 0.010%

    No Known Activations