Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76538
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     relev
    -0.07
    哈
    -0.07
     Id
    -0.07
    �
    -0.07
     Hann
    -0.07
    @Id
    -0.07
    捐助
    -0.07
    แชมป
    -0.06
    Ἷ
    -0.06
    /sn
    -0.06
    POSITIVE LOGITS
    .datetime
    0.08
    _lifetime
    0.07
    (short
    0.07
     completa
    0.07
     violet
    0.07
    ceptor
    0.07
    icios
    0.07
    _equals
    0.07
    可能な
    0.06
    zte
    0.06
    Activations Density 0.005%

    No Known Activations