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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    6. 75288
    Prev
    Next
    INDEX
    Explanations

    license agreement

    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
    看得
    -0.07
    ackbar
    -0.07
    �
    -0.07
    疑似
    -0.07
    넠
    -0.07
    HasBeen
    -0.07
    ',//
    -0.06
    :<
    -0.06
    ['_
    -0.06
    -aff
    -0.06
    POSITIVE LOGITS
     lis
    0.07
     plaster
    0.07
     Them
    0.07
    coin
    0.07
     inch
    0.07
    cream
    0.06
    هذه
    0.06
    source
    0.06
    eware
    0.06
     lowers
    0.06
    Activations Density 0.001%

    No Known Activations