INDEX

Explanations

references to time

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

unf

-0.31

emp

-0.29

 unfavorable

-0.28

 favorable

-0.28

æ°ª

-0.27

 States

-0.26

 favor

-0.26

ÐºÐ»Ð°Ð´

-0.26

imers

-0.26

emp

-0.25

POSITIVE LOGITS

éĥĵ

0.30

uger

0.27

uids

0.27

zioni

0.25

åħ¬çĦ¶

0.24

_beam

0.24

nte

0.24

ugi

0.24

 Conserv

0.24

olland

0.24

Activations Density 0.004%

references to time

No Comments

No Known Activations