INDEX

Explanations

flu

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

ikh

-0.28

_locals

-0.28

ovich

-0.28

 complexity

-0.27

 Complexity

-0.27

ligt

-0.27

å¼µè²¼

-0.26

éĴĹ

-0.26

cript

-0.26

“(

-0.25

POSITIVE LOGITS

æĦ

0.28

 suscept

0.28

éŃħ

0.25

Pack

0.24

_kw

0.24

wargs

0.24

SUS

0.24

uw

0.24

cw

0.24

å±£

0.24

Activations Density 0.017%

flu

No Comments

No Known Activations