© 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. 95994
    Prev
    Next
    INDEX
    Explanations

    Crus

    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
    åŃ³
    -0.28
     overturned
    -0.27
    åIJijå¾Ģ
    -0.26
    éļľ
    -0.26
    åij½
    -0.25
    éĢłç¦ı
    -0.24
    agem
    -0.24
    åŃº
    -0.24
     trouble
    -0.23
    abilia
    -0.23
    POSITIVE LOGITS
    èĦ±
    0.30
    aran
    0.28
    麦åħĭ
    0.27
     mel
    0.27
    çĶ²çĬ¶
    0.26
     McInt
    0.26
    篮
    0.25
    iare
    0.25
     McCoy
    0.25
    åIJĦ项
    0.25
    Activations Density 0.884%

    No Known Activations