© 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. 33-TRANSCODER-HP
    7. 53085
    Prev
    Next
    INDEX
    Explanations

    C

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @student
    -0.26
     kidding
    -0.26
     Rig
    -0.26
    触
    -0.25
    ball
    -0.25
    .za
    -0.25
    ä½İè°ĥ
    -0.24
    èĩª
    -0.24
    tet
    -0.24
    para
    -0.24
    POSITIVE LOGITS
     indemn
    0.28
    åĪ«
    0.28
    наÑĤ
    0.26
     nok
    0.26
     cu
    0.26
    åĪĹ
    0.26
    Matchers
    0.25
    纵
    0.25
    è¿ĺæĺ¯ä¼ļ
    0.24
    诲
    0.23
    Activations Density 0.004%

    No Known Activations