© 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. 15-RESID-POST-AA
    11. 26030
    Prev
    Next
    INDEX
    Explanations

    changes

    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
     conduit
    -0.07
     wand
    -0.07
     testim
    -0.07
     detected
    -0.07
    .ar
    -0.07
    Bridge
    -0.06
    rogram
    -0.06
    ('__
    -0.06
     Inspector
    -0.06
     będ
    -0.06
    POSITIVE LOGITS
    采用
    0.07
    URNS
    0.07
    بارك
    0.07
    上午
    0.06
    <t
    0.06
    (days
    0.06
     erupt
    0.06
    ✤
    0.06
    FG
    0.06
    :y
    0.06
    Activations Density 0.268%

    No Known Activations