© 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. 21029
    Prev
    Next
    INDEX
    Explanations

    4

    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
     gall
    -0.07
    国情
    -0.07
    统筹
    -0.07
    也有
    -0.07
     стра
    -0.07
     Halifax
    -0.06
    실
    -0.06
    隻
    -0.06
    uide
    -0.06
    /uploads
    -0.06
    POSITIVE LOGITS
     Npgsql
    0.07
    ℵ
    0.07
    '}↵↵
    0.07
    明确提出
    0.07
     },
    ↵
    ↵
    0.07
    	call
    0.06
    }-{
    0.06
    cid
    0.06
     TERMIN
    0.06
    ]},↵
    0.06
    Activations Density 0.006%

    No Known Activations