© 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. 29988
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    å±ħ
    -0.26
    softmax
    -0.26
    UTO
    -0.26
    åĴĮå¹³
    -0.26
    çĬ¶åħĥ
    -0.25
    qual
    -0.25
    Pitch
    -0.24
    æķ´é½IJ
    -0.23
    æ®ĩ
    -0.23
    “She
    -0.23
    POSITIVE LOGITS
    ÑĮÑİ
    0.29
     sc
    0.27
     lo
    0.26
    ä¸Ģäºĭ
    0.26
    /browser
    0.26
    bris
    0.25
    co
    0.25
    æī§æķĻ
    0.25
    combat
    0.24
    .si
    0.24
    Activations Density 1.418%

    No Known Activations