© 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. 9-TRANSCODER-HP
    7. 29554
    Prev
    Next
    INDEX
    Explanations

    sale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿĨ
    -0.28
    (inv
    -0.26
    ymax
    -0.26
    éĥ¨åĪĨåĨħ容
    -0.25
    miss
    -0.25
    acies
    -0.24
    è¶Ł
    -0.24
     inviting
    -0.24
    Invocation
    -0.24
     commod
    -0.24
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.28
    ä¸Ģ身
    0.25
    åİŁå§ĭ
    0.24
    å¿įåıĹ
    0.24
     Owens
    0.24
     Degrees
    0.23
    èĩªå·±
    0.23
    åı¦ä¸Ģ
    0.23
    ocz
    0.23
    liner
    0.23
    Activations Density 0.127%

    No Known Activations