© 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. 23-TRANSCODER-HP
    7. 24362
    Prev
    Next
    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ames
    -0.28
     PROVIDED
    -0.27
     setStatus
    -0.26
     Rodgers
    -0.25
    OAD
    -0.25
     statuses
    -0.24
    setStatus
    -0.24
    oS
    -0.24
    getStatus
    -0.24
    baugh
    -0.24
    POSITIVE LOGITS
    ="_
    0.28
     Abram
    0.27
     гÑĢ
    0.26
    _under
    0.25
     ext
    0.25
    è¾¹çķĮ
    0.25
    约
    0.24
    duct
    0.24
    å¤įä¹ł
    0.23
    äch
    0.23
    Activations Density 0.012%

    No Known Activations