© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75115
    Prev
    Next
    INDEX
    Explanations

    Chemistry

    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
    ("%
    -0.08
    飙升
    -0.07
    述职
    -0.07
     Increased
    -0.07
    ige
    -0.07
     reverse
    -0.07
    颡
    -0.07
    ❏
    -0.07
    umericUpDown
    -0.06
    splice
    -0.06
    POSITIVE LOGITS
    HU
    0.08
    CEF
    0.07
    𝙿
    0.07
     Huffington
    0.07
    工艺品
    0.07
    AMPL
    0.07
    (AT
    0.07
    انب
    0.07
    和尚
    0.07
     Rew
    0.07
    Activations Density 0.001%

    No Known Activations