© 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. 29865
    Prev
    Next
    INDEX
    Explanations

    poverty

    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
    å½°
    -0.28
    课ç¨ĭ
    -0.26
    .Undef
    -0.25
     unders
    -0.24
     кÑĥÑĢÑģ
    -0.24
    éĶ¤
    -0.24
    éĥ¨éŨ
    -0.23
    ãĤĴå¤īãģĪ
    -0.23
    ctl
    -0.23
     testName
    -0.23
    POSITIVE LOGITS
    伸ãģ³
    0.28
    rell
    0.26
     ElementType
    0.25
    æķĪçĽĬ
    0.25
    panse
    0.25
    ä¸į管
    0.24
    agu
    0.24
    _mp
    0.24
    éĩijéĴ±
    0.24
    _RG
    0.23
    Activations Density 0.163%

    No Known Activations