© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 102637
    Prev
    Next
    INDEX
    Explanations

    code divider

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eyJ
    -0.08
    海外市场
    -0.07
    毛孔
    -0.07
    乳房
    -0.07
     посколь
    -0.07
    内外
    -0.07
    颔
    -0.07
    阳区
    -0.06
     sensitivity
    -0.06
    虚
    -0.06
    POSITIVE LOGITS
    Reduc
    0.07
     mec
    0.07
    olic
    0.07
    asp
    0.06
    orte
    0.06
     consegu
    0.06
    Logic
    0.06
     علي
    0.06
    olvable
    0.06
    �
    0.06
    Activations Density 0.013%

    No Known Activations