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. 85686
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    تمثل
    -0.08
     eclipse
    -0.06
     thirds
    -0.06
     WikiLeaks
    -0.06
     bölgesinde
    -0.06
     válido
    -0.06
    EUR
    -0.06
     administer
    -0.06
     Vide
    -0.06
     valido
    -0.06
    POSITIVE LOGITS
    AIT
    0.07
    咆
    0.07
    .values
    0.07
     כא
    0.07
    remium
    0.07
    finally
    0.07
    _GEN
    0.07
    卡
    0.07
    _TR
    0.07
    已经
    0.07
    Activations Density 0.086%

    No Known Activations