© 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. 29939
    Prev
    Next
    INDEX
    Explanations

    charged

    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
    æĻķ
    -0.28
     suppose
    -0.26
    人身
    -0.26
     nir
    -0.25
     domina
    -0.25
     Cru
    -0.25
    -transition
    -0.25
    rena
    -0.24
    orer
    -0.23
    _strip
    -0.23
    POSITIVE LOGITS
    两æīĭ
    0.29
    Metric
    0.26
     */,↵
    0.25
     proport
    0.25
    illa
    0.25
    inger
    0.25
    éĢļè¿ĩ
    0.25
    iment
    0.25
    æķ£
    0.24
    éĺĻ
    0.24
    Activations Density 2.325%

    No Known Activations