© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15-RESID-POST-AA
    11. 126837
    Prev
    Next
    INDEX
    Explanations

    ’s is

    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
    每当
    -0.08
    ئت
    -0.08
    뒬
    -0.08
    .escape
    -0.07
    董事
    -0.07
    activo
    -0.07
    띡
    -0.07
     Geschä
    -0.07
     damit
    -0.07
    cip
    -0.07
    POSITIVE LOGITS
    연구
    0.08
    rame
    0.08
     myocard
    0.08
    Acc
    0.07
    石家庄
    0.07
     Cyan
    0.07
    Ping
    0.07
     Rpc
    0.07
    TERNAL
    0.07
    	g
    0.07
    Activations Density 0.027%

    No Known Activations