INDEX

Explanations

Cast

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

å¤´çĹĽ

-0.30

TAR

-0.27

è¾ĵåħ¥

-0.26

pread

-0.26

orts

-0.25

Tar

-0.25

onica

-0.25

tar

-0.24

 thunder

-0.24

.readInt

-0.24

POSITIVE LOGITS

ule

0.28

sla

0.26

ure

0.24

æĮ¤

0.24

æ·¹

0.23

uslim

0.23

less

0.23

éĥħ

0.23

ULE

0.23

 wraps

0.23

Activations Density 0.005%

Cast

No Comments

No Known Activations