© 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. 150281
    Prev
    Next
    INDEX
    Explanations

    Names starting with Rand

    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
    armed
    -0.27
    æŁIJç§įç¨ĭ度
    -0.25
    åĪĨ辨
    -0.25
    estre
    -0.25
    æĹłæķ°æ¬¡
    -0.25
    finder
    -0.24
    atan
    -0.24
    fin
    -0.24
    çģµæ´»
    -0.24
    çľĭä¸Ģä¸ĭ
    -0.24
    POSITIVE LOGITS
    ÃŃsticas
    0.28
    ency
    0.26
     floats
    0.25
    utton
    0.25
    raft
    0.25
    vid
    0.24
    iggins
    0.24
     па
    0.23
    uttle
    0.23
    以èī²
    0.23
    Activations Density 0.298%

    No Known Activations