© 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. 23-RESID-POST-AA
    6. 802
    Prev
    Next
    INDEX
    Explanations

    Informal conversation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     następn
    -0.07
    	DWORD
    -0.07
    对于
    -0.07
    选定
    -0.07
    Miss
    -0.06
    .allocate
    -0.06
     punto
    -0.06
     ди
    -0.06
     triplet
    -0.06
    ()]↵↵
    -0.06
    POSITIVE LOGITS
    getCode
    0.07
     refund
    0.07
     р
    0.07
    حض
    0.07
     synd
    0.06
    subcategory
    0.06
    工業
    0.06
    分销
    0.06
    겚
    0.06
    ⽉
    0.06
    Activations Density 0.066%

    No Known Activations