INDEX

Explanations

paper

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

Paper

-0.34

paper

-0.32

 paper

-0.32

.paper

-0.30

pdf

-0.30

 Paper

-0.29

 papers

-0.29

_paper

-0.28

_tbl

-0.28

çº¸

-0.28

POSITIVE LOGITS

çī¹æ´¾

0.27

åĿļåĽº

0.25

elsea

0.25

bed

0.24

 Teeth

0.24

XII

0.24

.lift

0.24

FX

0.24

FG

0.23

uilt

0.23

Activations Density 0.157%

paper

No Comments

No Known Activations