© 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. 69047
    Prev
    Next
    INDEX
    Explanations

    Addresses/locations

    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
    炻
    -0.08
    〴
    -0.07
    뉅
    -0.07
    .MIN
    -0.07
    —to
    -0.07
     Reflex
    -0.07
    唐代
    -0.07
    wand
    -0.06
     Clip
    -0.06
    瑔
    -0.06
    POSITIVE LOGITS
     תוכלו
    0.08
    pics
    0.07
     дома
    0.07
     whats
    0.07
     WHATSOEVER
    0.07
     POSIX
    0.07
    葩
    0.07
     gözü
    0.06
    serialized
    0.06
    🔊
    0.06
    Activations Density 0.008%

    No Known Activations