INDEX

Explanations

promises

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

.masks

-0.34

planes

-0.26

 masks

-0.26

probably

-0.25

MASK

-0.25

å¹³éĿ¢

-0.25

suming

-0.25

ixon

-0.24

typeid

-0.24

 latina

-0.24

POSITIVE LOGITS

olla

0.26

landÄ±r

0.25

ymb

0.25

åĳĬ

0.25

Hair

0.25

èªĵ

0.25

eway

0.25

Ð»Ð°ÑĤ

0.24

rok

0.24

edList

0.24

Activations Density 0.013%

promises

No Comments

No Known Activations