INDEX

Explanations

going

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

å°ıä¼Ļä¼´

-0.25

é©¬ä¸ģ

-0.25

ç¼ºåı£

-0.24

Wizard

-0.24

 wizard

-0.24

PARAM

-0.24

ITOR

-0.24

 pesso

-0.24

 Wizard

-0.24

agn

-0.24

POSITIVE LOGITS

gri

0.28

éĽ¨æ°´

0.25

.priority

0.25

uids

0.25

eve

0.24

çĶ³è´Ń

0.24

 rewrite

0.24

 intermedi

0.23

 richer

0.23

 priority

0.23

Activations Density 0.009%

going

No Comments

No Known Activations