© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17837
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    儿女
    -0.08
    inds
    -0.07
    edriver
    -0.07
    卺
    -0.07
    务必
    -0.07
    万达
    -0.07
    .jsdelivr
    -0.07
     usted
    -0.07
    萏
    -0.07
    暖气
    -0.07
    POSITIVE LOGITS
     gr
    0.07
    مسألة
    0.07
    _logits
    0.07
    ង
    0.07
    nonatomic
    0.07
    Angles
    0.06
     ???
    0.06
     Attachment
    0.06
    ughs
    0.06
    物质
    0.06
    Activations Density 0.062%

    No Known Activations