INDEX

Explanations

thon

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NC

-0.29

NC

-0.29

æħ°

-0.26

Parts

-0.25

opl

-0.25

Yue

-0.25

è¹²

-0.24

NEY

-0.24

 prototypes

-0.24

 parts

-0.24

POSITIVE LOGITS

åĨķ

0.29

æĽ²

0.27

UILayout

0.27

ç»ļ

0.27

çİĩä¸º

0.26

 cosm

0.26

 introduced

0.26

cur

0.25

filer

0.24

outh

0.24

Activations Density 0.058%

thon

No Comments

No Known Activations