© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95218
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¢Ĺ
    -0.28
    erg
    -0.27
    è±Ĩ
    -0.27
    çĽ¸ä¿¡
    -0.26
    Vari
    -0.26
    é¡Ĩ
    -0.26
    说åĪ°
    -0.25
    对èĩªå·±
    -0.25
    åħ³èĬĤ
    -0.25
    é¢Ĺç²Ĵ
    -0.25
    POSITIVE LOGITS
    fec
    0.27
    GER
    0.26
    *time
    0.25
    edis
    0.25
    splice
    0.25
    nin
    0.24
    äºĶåįģ
    0.24
     bere
    0.24
    scss
    0.24
    ç²ķ
    0.24
    Activations Density 0.000%

    No Known Activations