© 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. 11-RESID-POST-AA
    11. 22413
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    几个月
    -0.07
    _PREF
    -0.07
     migli
    -0.06
     kẻ
    -0.06
     olduğunu
    -0.06
     isFirst
    -0.06
    NSS
    -0.06
    ▐
    -0.06
     Bracket
    -0.06
    pas
    -0.06
    POSITIVE LOGITS
     comprising
    0.09
    .DataBindings
    0.08
    中文
    0.07
    stdafx
    0.07
     philosoph
    0.07
     lname
    0.07
    .sulake
    0.07
    \Database
    0.07
    陴
    0.07
     lxml
    0.07
    Activations Density 0.025%

    No Known Activations