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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    6. 69810
    Prev
    Next
    INDEX
    Explanations

    Of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    czną
    -0.07
     initialState
    -0.07
     Vor
    -0.07
     arrog
    -0.07
    maf
    -0.07
    JV
    -0.06
    Tags
    -0.06
    gmail
    -0.06
    Egypt
    -0.06
    $mail
    -0.06
    POSITIVE LOGITS
    产妇
    0.08
    ienie
    0.08
     setbacks
    0.07
    _si
    0.07
    のは
    0.07
     모두
    0.07
    ancers
    0.07
    �
    0.07
    였다
    0.07
    _lost
    0.07
    Activations Density 0.002%

    No Known Activations