© 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. 76038
    Prev
    Next
    INDEX
    Explanations

    @Component

    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
     advers
    -0.07
    סיר
    -0.07
     :)↵↵
    -0.07
     Apprent
    -0.07
    选出
    -0.07
     obtained
    -0.06
    assuming
    -0.06
    next
    -0.06
    layer
    -0.06
    禀
    -0.06
    POSITIVE LOGITS
    makt
    0.08
    Floating
    0.07
    🎛
    0.07
     freeing
    0.07
     Floating
    0.07
     illness
    0.07
    jandro
    0.06
     Asians
    0.06
    功德
    0.06
     poate
    0.06
    Activations Density 0.002%

    No Known Activations