INDEX

Explanations

Code, math, and documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

äººæķ°

-0.56

 fewer

-0.54

åħ±æľī

-0.50

 numberOf

-0.49

NumberOf

-0.49

æķ°çĽ®

-0.48

å¤ļè¾¾

-0.48

assertCount

-0.47

æĢ»æķ°

-0.46

.numberOf

-0.45

POSITIVE LOGITS

Exact

0.27

earer

0.25

æĪĳå¿ĥéĩĮ

0.25

exact

0.24

ynamics

0.24

errer

0.23

 Exact

0.23

IFE

0.23

imas

0.23

 boosting

0.23

Activations Density 0.001%

Code, math, and documentation

No Comments

No Known Activations