© 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. 27-TRANSCODER-HP
    7. 8315
    Prev
    Next
    INDEX
    Explanations

    ):

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŶä¸į
    -0.26
    亲çĪ±
    -0.26
     Diss
    -0.26
     base
    -0.25
    ######
    -0.24
    orama
    -0.24
     bases
    -0.24
    á»ĥn
    -0.23
     bas
    -0.23
     diss
    -0.23
    POSITIVE LOGITS
    super
    0.49
     super
    0.43
    	super
    0.42
    è¶ħ级
    0.39
    (super
    0.39
    è¶ħ
    0.38
    Super
    0.35
    _super
    0.35
    .super
    0.34
    ãĤ¹ãĥ¼ãĥij
    0.32
    Activations Density 0.122%

    No Known Activations