© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 953
    Prev
    Next
    INDEX
    Explanations

    %.

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iolet
    -0.07
    root
    -0.07
    True
    -0.07
    *A
    -0.07
     burnt
    -0.07
    yaml
    -0.07
    .Transparent
    -0.06
    =file
    -0.06
    %A
    -0.06
    但这
    -0.06
    POSITIVE LOGITS
     нашей
    0.07
     Changing
    0.07
    ░
    0.06
     מש
    0.06
    กด
    0.06
     [↵↵
    0.06
     load
    0.06
     '\\'
    0.06
    打击
    0.06
    boom
    0.06
    Activations Density 0.000%

    No Known Activations