INDEX

Explanations

technical documents

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

req

-0.29

vap

-0.28

ocop

-0.27

BUM

-0.25

ocumented

-0.25

ep

-0.24

uche

-0.24

pup

-0.24

çĥĬ

-0.24

isas

-0.23

POSITIVE LOGITS

 ì·¨

0.28

IW

0.28

StringValue

0.27

plements

0.27

taken

0.26

.removeItem

0.25

æīĵå¥½

0.24

 taken

0.24

:str

0.24

å¿«è®¯

0.24

Activations Density 0.206%

technical documents

No Comments

No Known Activations