© 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. 98615
    Prev
    Next
    INDEX
    Explanations

    math

    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
    vre
    -0.31
    otypes
    -0.29
    ENO
    -0.28
    ä¸į足以
    -0.27
    ä¸įä¿¡
    -0.27
    ä¸ĢèĤ¡
    -0.25
    ä¸Ŀè·¯
    -0.25
    æŃ¦å£«
    -0.25
    åıªè§ģ
    -0.24
    eways
    -0.24
    POSITIVE LOGITS
    lify
    0.27
    ç¼ĺ
    0.27
     Lance
    0.25
    æŃ£å®Ĺ
    0.23
    _TAC
    0.23
     cott
    0.23
     chaining
    0.23
    éĵ
    0.23
    classic
    0.23
    @a
    0.22
    Activations Density 0.001%

    No Known Activations