INDEX

Explanations

attributes/locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

æīĢèĥ½

-0.30

blr

-0.28

ofile

-0.27

çļĦçħ§çīĩ

-0.26

ton

-0.26

elon

-0.25

Ree

-0.25

posiÃ§Ã£o

-0.25

prite

-0.25

organic

-0.24

POSITIVE LOGITS

rz

0.28

({_

0.27

 later

0.25

ho

0.25

ë°±

0.25

fv

0.25

aml

0.24

 Asked

0.23

 ÑĤÑĢÐµÐ±Ð¾Ð²Ð°Ð½Ð¸Ñı

0.23

Py

0.23

Activations Density 47.942%

attributes/locations

No Comments

No Known Activations