© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28565
    Prev
    Next
    INDEX
    Explanations

    _AUX

    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
    вен
    -0.07
    seau
    -0.07
    ikel
    -0.07
     tóc
    -0.07
    resa
    -0.06
    -focus
    -0.06
     sponsor
    -0.06
    (e
    -0.06
    endant
    -0.06
     recherche
    -0.06
    POSITIVE LOGITS
    arro
    0.07
    行星
    0.07
    нолог
    0.07
     conforme
    0.07
    ,UnityEngine
    0.07
    浬
    0.07
    หมาย
    0.07
     Advertising
    0.06
    비용
    0.06
     ----------
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.