© 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. 11-RESID-POST-AA
    11. 24160
    Prev
    Next
    INDEX
    Explanations

    oaths and swearing-in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Channels
    -0.07
    	RTCK
    -0.07
    _Login
    -0.07
    .lift
    -0.07
    <center
    -0.06
    stdout
    -0.06
    .issue
    -0.06
    Another
    -0.06
     Helpers
    -0.06
     Archive
    -0.06
    POSITIVE LOGITS
     ballot
    0.07
    馘
    0.06
    营业额
    0.06
    aul
    0.06
    双脚
    0.06
    ura
    0.06
    -deals
    0.06
    halb
    0.06
    endale
    0.06
     clan
    0.06
    Activations Density 0.012%

    No Known Activations