© 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. 24575
    Prev
    Next
    INDEX
    Explanations

    obtaining

    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
    erties
    -0.29
    æīįæĺ¯çľŁæŃ£
    -0.28
    itness
    -0.28
    lds
    -0.28
    [++
    -0.27
    detect
    -0.26
     spontaneously
    -0.26
    åĪĹ
    -0.26
    aset
    -0.25
    Integrated
    -0.25
    POSITIVE LOGITS
    æģ°å¥½
    0.36
     exactly
    0.33
     exact
    0.31
    è¶³å¤ŁçļĦ
    0.31
    æľīè¶³å¤ŁçļĦ
    0.29
    æģ°
    0.29
    æŃ£å¥½
    0.28
     Exactly
    0.28
    æģ°å½ĵ
    0.27
    åIJĪéĢĤçļĦ
    0.27
    Activations Density 0.005%

    No Known Activations