© 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. 24436
    Prev
    Next
    INDEX
    Explanations

    medical/academic reports

    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
    ady
    -0.35
    s
    -0.32
    raft
    -0.28
    down
    -0.28
    soup
    -0.27
    ilda
    -0.27
    sheets
    -0.26
    slope
    -0.26
    sign
    -0.25
    æĮijéĢī
    -0.24
    POSITIVE LOGITS
    RAIN
    0.26
    åŃĹ
    0.25
    çĮ©
    0.25
    	resource
    0.24
    cth
    0.24
    Night
    0.24
    )(_
    0.24
    chten
    0.24
    éĤ£ä¹Īç®Ģåįķ
    0.24
    Emp
    0.23
    Activations Density 0.002%

    No Known Activations