© 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. 15-RESID-POST-AA
    6. 123169
    Prev
    Next
    INDEX
    Explanations

    of

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    D
    -0.08
    (seed
    -0.07
     Bed
    -0.07
    .getString
    -0.07
     D
    -0.07
    EX
    -0.07
     TN
    -0.07
     FOR
    -0.07
    DEV
    -0.07
    爱好
    -0.07
    POSITIVE LOGITS
    ithe
    0.07
    תרבות
    0.07
    ификаци
    0.07
     perman
    0.07
     נשאר
    0.07
    riet
    0.06
    ême
    0.06
     maneu
    0.06
    chè
    0.06
    .FormStartPosition
    0.06
    Activations Density 0.009%

    No Known Activations