© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 129616
    Prev
    Next
    INDEX
    Explanations

    Chemical nomenclature

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owns
    -0.08
    MPI
    -0.07
    מסמכי
    -0.07
    ᐁ
    -0.07
    ('').
    -0.07
    appointment
    -0.07
     Arkadaş
    -0.06
    魔兽
    -0.06
     nail
    -0.06
     równ
    -0.06
    POSITIVE LOGITS
    (chars
    0.07
     Please
    0.07
    ומ
    0.07
     ellas
    0.06
     Alexis
    0.06
    _util
    0.06
     Lob
    0.06
    樱桃
    0.06
     họ
    0.06
     TB
    0.06
    Activations Density 0.002%

    No Known Activations