INDEX

Explanations

Negative consequences/trade-offs

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

 nhá»ĭ

-0.30

ICY

-0.28

argas

-0.26

quam

-0.26

ä¸Ģæīĭ

-0.25

Cyc

-0.25

éĩĩæĳĺ

-0.24

ä¸ĢäºĮ

-0.24

çļĭ

-0.24

ÙĦØ³

-0.24

POSITIVE LOGITS

Env

0.26

isle

0.26

å½ķ

0.26

ater

0.26

#endregion

0.25

cr

0.25

 mutable

0.24

Env

0.24

 assumption

0.24

"context

0.24

Activations Density 0.001%

Negative consequences/trade-offs

No Comments

No Known Activations