INDEX

Explanations

software licenses, encyclopedia entries

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¤ļåľ°

-0.27

ICES

-0.27

ä¼Ĭæĸ¯

-0.26

éĿŀå¸¸å¤ļçļĦ

-0.26

 applicable

-0.25

åı¯æİ§

-0.25

 mock

-0.24

çŀ³

-0.24

Cleanup

-0.24

ording

-0.24

POSITIVE LOGITS

mpr

0.26

.Arguments

0.25

google

0.24

 arguing

0.24

åĴ¤

0.23

 Prem

0.23

åĽĽä¸ªæĦıè¯Ĩ

0.23

 Arguments

0.23

gb

0.23

ãģ£ãģ¡ãĤĥ

0.23

Activations Density 0.008%

software licenses, encyclopedia entries

No Comments

No Known Activations