INDEX

Explanations

computer code

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

anced

-0.28

.tool

-0.25

 Hurricanes

-0.25

tool

-0.25

 inflater

-0.24

clude

-0.24

 tool

-0.24

CLUDE

-0.24

éŁ¿

-0.23

ç¾İæĻ¯

-0.23

POSITIVE LOGITS

åĽ¢ç»ĵ

0.27

(()

0.27

#/

0.26

å¯¸

0.25

 Operations

0.25

éĤ£æ¬¡

0.24

æ£ł

0.24

ewan

0.24

åĪ«

0.24

cz

0.24

Activations Density 0.027%

computer code

No Comments

No Known Activations