© 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. 12-TRANSCODER-HP
    7. 22483
    Prev
    Next
    INDEX
    Explanations

    flavor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİ·
    -0.29
    æµ´
    -0.29
    被æįķ
    -0.26
    rego
    -0.25
     summoned
    -0.25
     Geh
    -0.24
    èĪĪ
    -0.24
    被æĬĵ
    -0.24
    çªĿ
    -0.24
     housing
    -0.23
    POSITIVE LOGITS
    nowled
    0.27
     lax
    0.27
    å¢ŀè¿Ľ
    0.26
    æĶ»çķ¥
    0.25
    виÑĤ
    0.25
    jp
    0.24
    ṡ
    0.23
    credit
    0.23
    客家
    0.23
    ibs
    0.22
    Activations Density 0.000%

    No Known Activations