© 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. 95407
    Prev
    Next
    INDEX
    Explanations

    J

    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
    loom
    -0.27
    pcf
    -0.27
    为人
    -0.27
    å§Ĵ
    -0.27
    olis
    -0.27
    olls
    -0.27
    è§Ĥ
    -0.25
    åī©
    -0.25
    ëĶľ
    -0.25
    积
    -0.25
    POSITIVE LOGITS
    èĤ¡
    0.30
    elle
    0.29
    çi
    0.28
    bounded
    0.26
     bounded
    0.25
    lemn
    0.25
    iedades
    0.24
     roman
    0.24
    lex
    0.24
     useHistory
    0.24
    Activations Density 0.103%

    No Known Activations