INDEX

Explanations

ophilia

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

 distinct

-0.28

fin

-0.26

bags

-0.25

tex

-0.25

é£İæīĩ

-0.25

Distinct

-0.25

.shadow

-0.24

distinct

-0.24

 Investigators

-0.24

LIC

-0.24

POSITIVE LOGITS

orks

0.27

ORK

0.26

-*-

0.25

istically

0.25

åľ°ä¸Ń

0.25

BDS

0.24

annie

0.24

idal

0.24

æ¯ıå¤©éĥ½

0.24

inas

0.23

Activations Density 0.121%

ophilia

No Comments

No Known Activations