INDEX

Explanations

comma

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

 ceilings

-0.26

sk

-0.26

éĢł

-0.26

 pans

-0.25

big

-0.25

 batt

-0.25

çĽ´æİ¥å½±åĵį

-0.25

Bib

-0.25

åĮĹå¤§

-0.24

,:,

-0.24

POSITIVE LOGITS

èĤ±

0.27

ippo

0.26

 requestOptions

0.25

vero

0.25

QRSTUV

0.25

èł¹

0.25

 Millenn

0.24

cente

0.24

æĦļ

0.24

å·¦ä¾§

0.24

Activations Density 0.024%

comma

No Comments

No Known Activations