© 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. 30-TRANSCODER-HP
    7. 95701
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    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
    erie
    -0.28
     conflic
    -0.27
    rie
    -0.26
    ç»ĵ
    -0.26
    èijĹ
    -0.25
    ainen
    -0.25
     //~
    -0.25
    ä¸įå±ij
    -0.24
    ocator
    -0.24
    ouse
    -0.24
    POSITIVE LOGITS
    éĶµ
    0.26
    done
    0.26
    éĥ½å¸Ĥ
    0.24
    jar
    0.23
     Emer
    0.23
     hue
    0.23
    åĽŀæĿ¥
    0.23
     loss
    0.23
    hue
    0.23
    des
    0.23
    Activations Density 0.102%

    No Known Activations