© 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. 24-TRANSCODER-HP
    7. 150887
    Prev
    Next
    INDEX
    Explanations

    to be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĻ
    -0.52
    ï¼ĮåĪĻ
    -0.48
     then
    -0.47
    åĪĻæĺ¯
    -0.47
    åīĩ
    -0.43
     THEN
    -0.42
    then
    -0.42
     entonces
    -0.41
    	then
    -0.39
     Then
    -0.38
    POSITIVE LOGITS
     complex
    0.28
    MISS
    0.26
    ascript
    0.26
    gor
    0.26
    iel
    0.25
    holding
    0.25
    ilo
    0.25
    æ°ijäºĭ
    0.24
     z
    0.24
     sed
    0.24
    Activations Density 0.896%

    No Known Activations