© 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. 19-RESID-POST-AA
    11. 68738
    Prev
    Next
    INDEX
    Explanations

    ly and weak

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anlaşıl
    -0.09
    שיל
    -0.08
    .until
    -0.08
    __.'/
    -0.07
    흫
    -0.07
    architecture
    -0.07
    時には
    -0.07
    CastException
    -0.07
    нская
    -0.07
    بريط
    -0.07
    POSITIVE LOGITS
     Game
    0.08
    硬件
    0.07
     مق
    0.07
    *
    0.07
     robotic
    0.07
     bro
    0.07
     ego
    0.07
     mat
    0.07
     سم
    0.07
     residents
    0.07
    Activations Density 0.057%

    No Known Activations