INDEX

Explanations

activation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Crypt

-0.30

crypt

-0.29

 Crypt

-0.27

aghetti

-0.26

 crypt

-0.25

éģĹæĨ¾

-0.25

CRYPT

-0.25

.encrypt

-0.25

æİĽãģĳ

-0.25

yat

-0.24

POSITIVE LOGITS

 Winter

0.27

 Cond

0.27

 cond

0.26

 termin

0.24

 Constant

0.24

 Irving

0.24

æ¶§

0.24

(pc

0.24

-cond

0.24

è°·

0.24

Activations Density 0.009%

activation

No Comments

No Known Activations