© 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. 23-TRANSCODER-HP
    7. 23819
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬ç¤º
    -0.30
    é«ĺæłĩåĩĨ
    -0.29
     Hoch
    -0.26
    åĨ²æ´Ĺ
    -0.26
    è§īå¾Ĺèĩªå·±
    -0.26
    èİł
    -0.25
    æ¥ŀ
    -0.25
    MemoryWarning
    -0.25
    è¿ĻçĤ¹
    -0.25
    æ¾Ħæ¸ħ
    -0.24
    POSITIVE LOGITS
     resort
    0.41
    ç§ģ
    0.33
     resorts
    0.31
     Vern
    0.30
    寻æ±Ĥ
    0.30
    æ±ĤåĬ©
    0.29
     desperate
    0.29
    éĵ¤
    0.29
     opport
    0.29
    BREAK
    0.28
    Activations Density 0.006%

    No Known Activations