© 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. 24300
    Prev
    Next
    INDEX
    Explanations

    seek

    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
    èĻ¹æ¡¥
    -0.30
     exponentially
    -0.28
    éĤ£è¾¹
    -0.25
    ivor
    -0.24
     intended
    -0.24
    åħ³æ³¨
    -0.24
    ober
    -0.23
    pm
    -0.23
    çĽ¾
    -0.23
    Art
    -0.23
    POSITIVE LOGITS
    DUCT
    0.28
    å·®è·Ŀ
    0.26
    	yy
    0.26
    duct
    0.25
     regard
    0.25
    ems
    0.25
    @include
    0.24
    .xticks
    0.24
    \xaa
    0.24
    /man
    0.24
    Activations Density 0.134%

    No Known Activations