© 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. 24850
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    çºłéĶĻ
    -0.27
    ForRow
    -0.26
     ele
    -0.25
    缩
    -0.25
    å®ĺæĸ¹å¾®ä¿¡
    -0.25
    ç®Ģ称
    -0.25
    abric
    -0.24
    .mm
    -0.24
     Job
    -0.24
    稳æŃ¥
    -0.24
    POSITIVE LOGITS
    认为
    0.31
    ilig
    0.30
    ikki
    0.28
    because
    0.27
    çĻĸ
    0.27
    epam
    0.26
    åĽłä¸ºå®ĥ
    0.26
     Kushner
    0.25
     luáºŃn
    0.24
    kan
    0.24
    Activations Density 0.003%

    No Known Activations