© 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. 26368
    Prev
    Next
    INDEX
    Explanations

    of

    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
    /dist
    -0.07
     mechanically
    -0.07
     clustering
    -0.07
    尽早
    -0.07
     Definitely
    -0.07
    老实
    -0.07
    擅自
    -0.07
    気
    -0.07
     cần
    -0.07
    发电机
    -0.07
    POSITIVE LOGITS
    _FB
    0.07
    охран
    0.07
    Reward
    0.06
    kre
    0.06
    댑
    0.06
    קד
    0.06
    _TOUCH
    0.06
    لاقات
    0.06
    بية
    0.06
    薇
    0.06
    Activations Density 0.003%

    No Known Activations