© 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. 39273
    Prev
    Next
    INDEX
    Explanations

    outdoors and travel

    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
     ücretsiz
    -0.06
    닮
    -0.06
    calloc
    -0.06
    各异
    -0.06
    RESET
    -0.06
    END
    -0.06
     switching
    -0.06
    훨
    -0.06
     permet
    -0.06
    띡
    -0.06
    POSITIVE LOGITS
    .optimizer
    0.07
    cars
    0.07
    杂志社
    0.07
    男性
    0.07
     moderators
    0.07
     entidad
    0.07
    (",",
    0.07
    provided
    0.07
    实体经济
    0.07
    editor
    0.07
    Activations Density 0.059%

    No Known Activations