INDEX

Explanations

computer-generated text

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

comput

-0.27

éĢģ

-0.27

ientes

-0.26

stores

-0.24

Mul

-0.24

annels

-0.24

een

-0.24

.backends

-0.24

eree

-0.23

ulk

-0.23

POSITIVE LOGITS

æĳĶ

0.26

 Rebellion

0.26

æĦıè¯Ĩ

0.25

æ°ĳæĦı

0.25

quisite

0.24

éľĩ

0.24

ä¹ĭæĦı

0.24

 exig

0.24

 exper

0.24

Imp

0.24

Activations Density 0.009%

computer-generated text

No Comments

No Known Activations