INDEX

Explanations

th

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

éĽĨè£ħ

-0.26

orges

-0.26

 assignment

-0.25

assignment

-0.25

Assignment

-0.25

 Assignment

-0.25

ieres

-0.25

å°±è¯´

-0.24

 pres

-0.24

erset

-0.24

POSITIVE LOGITS

 Mandarin

0.26

oner

0.25

ãĤ³ãĥ¼ãĥ

0.24

.Encode

0.24

stral

0.24

èĩ

0.24

 crÃ©dit

0.23

onic

0.23

tcp

0.23

istic

0.23

Activations Density 0.014%

th

No Comments

No Known Activations