© 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. 95947
    Prev
    Next
    INDEX
    Explanations

    Independent

    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
    Ã¤ÃŁ
    -0.35
    ä½Ĩä»İ
    -0.33
    OSP
    -0.29
    ä½Ĩä»ĸ
    -0.28
     adorn
    -0.26
    ä½Ĩ
    -0.26
    主ä¹ī
    -0.25
    amente
    -0.25
    edb
    -0.25
     but
    -0.24
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.29
    cus
    0.28
    etes
    0.27
     Rutgers
    0.26
    åĢ¡è®®
    0.26
    æ½Ľ
    0.25
    inceton
    0.25
    èĩªå·±åĸľæ¬¢
    0.25
     ourselves
    0.25
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.24
    Activations Density 0.103%

    No Known Activations