INDEX

Explanations

healthcare

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

åªµ

-0.27

lama

-0.27

çĲĨ

-0.25

 sweets

-0.25

 spared

-0.25

MUX

-0.25

fen

-0.24

çļĦçĲĨæĥ³

-0.24

(TYPE

-0.24

eve

-0.24

POSITIVE LOGITS

åİĭåĬĽ

0.29

åĶ¾

0.26

çĤĴ

0.26

 Mine

0.25

çĶ±æŃ¤

0.25

ISIBLE

0.24

æīĵåĵį

0.24

 discrete

0.23

 stressing

0.23

 drafts

0.23

Activations Density 0.036%

healthcare

No Comments

No Known Activations