Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 1826
    Prev
    Next
    INDEX
    Explanations

    standing

    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
    麹
    -0.08
    ffc
    -0.08
    凄
    -0.07
    HSV
    -0.07
    IVER
    -0.07
     vbox
    -0.07
    localhost
    -0.07
    (random
    -0.07
    �
    -0.07
    abbix
    -0.07
    POSITIVE LOGITS
    _locked
    0.07
    Standing
    0.07
     степени
    0.07
    Directed
    0.06
    院长
    0.06
    .textAlignment
    0.06
    词条
    0.06
    寫
    0.06
    manship
    0.06
    潍坊
    0.06
    Activations Density 0.005%

    No Known Activations