© 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. 23-RESID-POST-AA
    11. 1164
    Prev
    Next
    INDEX
    Explanations

    love

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    вали
    -0.07
    过去了
    -0.07
     rõ
    -0.07
     ייתכן
    -0.07
    绿水青山
    -0.07
    PEC
    -0.07
     buen
    -0.07
    空气中
    -0.07
    新西兰
    -0.07
    峨
    -0.07
    POSITIVE LOGITS
    ISH
    0.07
    Ṃ
    0.06
    .RequestMethod
    0.06
    Linear
    0.06
     themes
    0.06
     Rah
    0.06
    ylim
    0.06
    ,R
    0.06
    Lewis
    0.06
    转向
    0.06
    Activations Density 0.004%

    No Known Activations