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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 62257
    Prev
    Next
    INDEX
    Explanations

    tent

    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
     الحديد
    -0.08
    (names
    -0.08
    OLVE
    -0.07
    خمس
    -0.07
    "No
    -0.07
     Ivan
    -0.07
    “Yes
    -0.07
     Dam
    -0.07
     respectively
    -0.07
    	play
    -0.07
    POSITIVE LOGITS
     larg
    0.08
    .utility
    0.07
    افت
    0.07
    default
    0.07
    IRTH
    0.07
     pestic
    0.07
     skirt
    0.07
     militar
    0.07
     Singleton
    0.07
    Builder
    0.07
    Activations Density 0.007%

    No Known Activations