© 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. 24378
    Prev
    Next
    INDEX
    Explanations

    biological responses

    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
     standard
    -0.27
    æłĩåĩĨ
    -0.27
    arium
    -0.26
    常è§Ħ
    -0.26
     cov
    -0.25
    å®Ī
    -0.25
    ular
    -0.25
    ä¼łç»Ł
    -0.25
     pin
    -0.25
    standard
    -0.25
    POSITIVE LOGITS
    adamente
    0.28
    imately
    0.27
     secretion
    0.26
    åĩºæ±Ĺ
    0.26
    InstanceOf
    0.25
    ç¡®
    0.25
    ewire
    0.24
     asserting
    0.24
    è¨
    0.24
    赶快
    0.23
    Activations Density 0.002%

    No Known Activations