© 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. 29866
    Prev
    Next
    INDEX
    Explanations

    locations or southwest place names

    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
    umi
    -0.26
    ucer
    -0.25
    æĬĵæįķ
    -0.24
     filetype
    -0.24
     Jail
    -0.24
    -strong
    -0.24
    uci
    -0.23
    NDAR
    -0.23
    커
    -0.23
    ìĬ¤íģ¬
    -0.23
    POSITIVE LOGITS
     underground
    0.24
    è°Ķ
    0.24
     obligatory
    0.24
    åĴĮåıijå±ķ
    0.24
    ä¸įè§ģ
    0.24
    \Query
    0.23
    æĿĥéĩį
    0.23
     OPTIONAL
    0.23
    å¼¹
    0.23
    iest
    0.23
    Activations Density 0.634%

    No Known Activations