© 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. 15-RESID-POST-AA
    6. 49152
    Prev
    Next
    INDEX
    Explanations

    nutritional information

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acknowledging
    -0.07
     mourning
    -0.07
    ég
    -0.07
     masterpiece
    -0.07
    一个个
    -0.07
     abandon
    -0.07
    NotFoundError
    -0.07
     GB
    -0.07
     harbour
    -0.07
    芙蓉
    -0.07
    POSITIVE LOGITS
    랬
    0.08
    𝚃
    0.07
    깉
    0.07
     Curl
    0.07
    괭
    0.07
    .FindGameObjectWithTag
    0.07
    等
    0.07
    writeln
    0.07
     Wrocław
    0.07
    תן
    0.07
    Activations Density 0.025%

    No Known Activations