© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 2732
    Prev
    Next
    INDEX
    Explanations

    collaborative

    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
    Hop
    -0.07
     constants
    -0.07
    (buff
    -0.07
    测定
    -0.07
    	Console
    -0.07
    ימת
    -0.07
    二期
    -0.06
     Immediate
    -0.06
    EEE
    -0.06
    犸
    -0.06
    POSITIVE LOGITS
    user
    0.08
    ysters
    0.07
    VIS
    0.07
    schütz
    0.07
    яз
    0.07
    老旧小区
    0.06
    都非常
    0.06
     unnecessarily
    0.06
    erule
    0.06
     toxin
    0.06
    Activations Density 0.040%

    No Known Activations