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. 1870
    Prev
    Next
    INDEX
    Explanations

    newlines and carriage returns

    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
     disreg
    -0.07
    �
    -0.07
    .Android
    -0.07
    (z
    -0.06
    格外
    -0.06
     Ri
    -0.06
    으로
    -0.06
    etroit
    -0.06
    碌
    -0.06
    PCS
    -0.06
    POSITIVE LOGITS
    닮
    0.07
    хот
    0.07
    .fixture
    0.07
    Τ
    0.07
    术
    0.07
     girlfriend
    0.07
    .When
    0.07
     pharmacist
    0.07
    莎
    0.07
    commit
    0.07
    Activations Density 0.008%

    No Known Activations